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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enviar
    -0.07
    放弃了
    -0.06
    ♜
    -0.06
    inson
    -0.06
     Rp
    -0.06
    꿀
    -0.06
    .assertEqual
    -0.06
    .Init
    -0.06
    ורה
    -0.06
    جة
    -0.06
    POSITIVE LOGITS
    🕣
    0.07
    broker
    0.07
    OCK
    0.07
    ˯
    0.07
    泪水
    0.06
    usive
    0.06
    -cost
    0.06
    (padding
    0.06
     firebase
    0.06
    dex
    0.06
    Act Density 0.021%

    No Known Activations