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

    Neuronpedia

    INDEX
    Explanations

    SQL code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     academics
    -0.08
     نرم
    -0.08
    .Gson
    -0.08
     כש
    -0.07
    Decoder
    -0.07
     બોલ
    -0.07
     delegate
    -0.07
    าห
    -0.07
     politely
    -0.07
    _attention
    -0.07
    POSITIVE LOGITS
    lot
    0.08
     SKY
    0.08
    0.08
    机械
    0.07
     disruption
    0.07
     zák
    0.07
    tractor
    0.07
    loga
    0.07
     intensive
    0.07
     Jerusal
    0.07
    Act Density 0.002%
    No Known Activations