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

    Neuronpedia

    INDEX
    Explanations

    location names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruin
    -0.08
     उद्ध
    -0.08
    IID
    -0.08
     버튼
    -0.08
     pul
    -0.07
     पुल
    -0.07
     escaping
    -0.07
     საუკეთესო
    -0.07
    _NON
    -0.07
    haha
    -0.07
    POSITIVE LOGITS
     Warr
    0.08
     calibre
    0.08
    senal
    0.07
    izards
    0.07
    rosion
    0.07
    θε
    0.07
     costes
    0.07
    osal
    0.07
    olutions
    0.07
     advisers
    0.07
    Act Density 0.000%

    No Known Activations