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

    Neuronpedia

    INDEX
    Explanations

    nearest

    np_max-act · gemini-2.0-flash

    mathematical operations and concepts related to powers and roots.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     "{}
    -0.07
    =id
    -0.07
     соци
    -0.06
     Inbox
    -0.06
    Segue
    -0.06
     armies
    -0.06
     lateinit
    -0.06
    ------+------+
    -0.06
     Leipzig
    -0.06
    _labels
    -0.06
    POSITIVE LOGITS
     minimum
    0.07
    -Jul
    0.06
    erv
    0.06
    فران
    0.06
    -non
    0.06
    buttons
    0.06
     altering
    0.06
    .a
    0.06
    ев
    0.06
    =s
    0.06
    Act Density 0.002%

    No Known Activations