Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to occurrences of the verb “use” (and its close equivalents like Spanish “utilizar”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    inquiries related to code implementation for web applications and data handling processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    sampling
    -0.07
    DialogTitle
    -0.07
    Tel
    -0.07
    $app
    -0.07
     کوت
    -0.06
    вроп
    -0.06
     продовж
    -0.06
     triangle
    -0.06
     Yield
    -0.06
    munition
    -0.06
    POSITIVE LOGITS
    WO
    0.07
     po
    0.06
     pioneers
    0.06
    _Cell
    0.06
    oub
    0.06
    �
    0.06
     violently
    0.06
    ​​
    0.06
    а�
    0.06
    aN
    0.06
    Act Density 0.049%

    No Known Activations