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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Κο
    -0.07
    .Str
    -0.06
     breeds
    -0.06
    uevo
    -0.06
     collided
    -0.06
    elled
    -0.06
    -funded
    -0.06
    optim
    -0.06
     Mam
    -0.05
     Gaw
    -0.05
    POSITIVE LOGITS
    .just
    0.07
    辛
    0.06
     بق
    0.06
     Occup
    0.06
    міні
    0.06
     Hij
    0.06
    HELP
    0.06
     روح
    0.06
    @Getter
    0.06
    روب
    0.06
    Act Density 0.044%

    No Known Activations