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

    Neuronpedia

    INDEX
    Explanations

    writing prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Authority
    -0.07
     admits
    -0.07
     Fiscal
    -0.07
    ガ
    -0.07
    �
    -0.07
    _projection
    -0.06
    -makers
    -0.06
     editions
    -0.06
     Moves
    -0.06
     positional
    -0.06
    POSITIVE LOGITS
     Preis
    0.07
     عملية
    0.06
    undred
    0.06
    chef
    0.06
     fel
    0.06
     Maxim
    0.06
     kosten
    0.06
     synd
    0.06
    .gson
    0.06
     entrev
    0.06
    Act Density 0.063%

    No Known Activations