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

    Neuronpedia

    INDEX
    Explanations

    equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    وجه
    -0.06
    useRalativeImagePath
    -0.06
    よ
    -0.06
    	right
    -0.06
     آنچه
    -0.06
    bj
    -0.06
    ruba
    -0.06
     hurt
    -0.06
    generator
    -0.06
    setw
    -0.06
    POSITIVE LOGITS
    .rx
    0.07
    Yellow
    0.06
     Co
    0.06
    OKEN
    0.06
    ribly
    0.06
    _JO
    0.06
     �
    0.06
     nalez
    0.06
    >>>>
    0.06
     intuitive
    0.06
    Act Density 0.040%

    No Known Activations