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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects the opening “To the” phrase as in “To the Editor:” at the start of letters.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    )||
    -0.07
     Vacuum
    -0.06
    izador
    -0.06
    etAddress
    -0.06
     annunci
    -0.06
     hã
    -0.06
     �
    -0.06
    eč
    -0.06
    rün
    -0.06
    _scope
    -0.06
    POSITIVE LOGITS
    (isinstance
    0.07
    .capacity
    0.06
    (By
    0.06
    .fil
    0.06
     اجرا
    0.06
     Wordpress
    0.06
     "!
    0.06
    _KEYWORD
    0.06
     NgModule
    0.06
    _np
    0.05
    Act Density 0.021%

    No Known Activations