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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ampil
    -0.07
     lui
    -0.06
    Govern
    -0.06
    olk
    -0.06
     Screen
    -0.06
    чий
    -0.06
     DIRECT
    -0.06
    OL
    -0.06
     Deliver
    -0.06
    .adapter
    -0.06
    POSITIVE LOGITS
    anut
    0.06
    /goto
    0.06
     banda
    0.06
    _ACTIV
    0.06
    -प
    0.06
    �
    0.06
     الملك
    0.06
     painfully
    0.06
    帝
    0.06
    Oracle
    0.06
    Act Density 0.003%

    No Known Activations