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

    Neuronpedia

    INDEX
    Explanations

    Code returning a value

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     technology
    -0.07
    imen
    -0.07
    我认为
    -0.07
    ìn
    -0.07
    مين
    -0.07
     max
    -0.07
    _cross
    -0.07
     Fetish
    -0.07
    ood
    -0.06
     rnd
    -0.06
    POSITIVE LOGITS
    ほとんど
    0.07
    쩻
    0.07
     airflow
    0.06
     polarity
    0.06
    .showError
    0.06
     trabajar
    0.06
     Strength
    0.06
    igrationBuilder
    0.06
    איכות
    0.06
    ҕ
    0.06
    Act Density 0.034%

    No Known Activations