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

    Neuronpedia

    INDEX
    Explanations

    say "w"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BUR
    -0.06
     �
    -0.06
     cl
    -0.06
     Soldiers
    -0.06
    F
    -0.06
    avan
    -0.06
     parseFloat
    -0.06
     bridges
    -0.06
    (volume
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    那里
    0.07
     Yugosl
    0.07
    Cors
    0.06
     ketogenic
    0.06
     kê
    0.06
    .tb
    0.06
    esteem
    0.06
    arter
    0.06
    stoi
    0.06
     活
    0.06
    Act Density 0.468%

    No Known Activations