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

    Neuronpedia

    INDEX
    Explanations

    predictions and betting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roofing
    -0.06
     Date
    -0.06
     deferred
    -0.06
     interior
    -0.06
     pads
    -0.06
     implants
    -0.06
     starter
    -0.06
     accounts
    -0.06
     Stanton
    -0.06
    ke
    -0.06
    POSITIVE LOGITS
    （笑
    0.08
     rej
    0.07
    &view
    0.07
    ząd
    0.07
     JSONException
    0.07
    manı
    0.07
     columnHeader
    0.06
    .Experimental
    0.06
     درد
    0.06
    .setdefault
    0.06
    Act Density 0.158%

    No Known Activations