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

    Neuronpedia

    INDEX
    Explanations

    ocose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrestlers
    -0.07
    (packet
    -0.06
     slut
    -0.06
    ış
    -0.06
     тела
    -0.06
     nods
    -0.06
    House
    -0.06
    ”的
    -0.06
    .Mutable
    -0.06
     čer
    -0.06
    POSITIVE LOGITS
    uin
    0.07
     Instructions
    0.06
    ined
    0.06
     invitation
    0.06
    чины
    0.06
    in
    0.06
     تاریخی
    0.06
    eless
    0.06
    當
    0.06
    ulado
    0.06
    Act Density 0.000%

    No Known Activations