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

    Neuronpedia

    INDEX
    Explanations

    cgi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    door
    -0.08
     daar
    -0.08
     Smoke
    -0.07
     Lod
    -0.07
     Keep
    -0.07
     Although
    -0.07
     doen
    -0.07
     true
    -0.07
     hoje
    -0.06
     Gui
    -0.06
    POSITIVE LOGITS
     pundits
    0.07
    :host
    0.07
    抚摸
    0.07
     �
    0.07
    ショップ
    0.07
    女人
    0.07
     Fishing
    0.07
     rhetoric
    0.07
    /install
    0.07
    .eql
    0.06
    Act Density 0.001%

    No Known Activations