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

    Neuronpedia

    INDEX
    Explanations

    inclusion/exclusion criteria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _successful
    -0.07
    WHERE
    -0.07
    plaintext
    -0.07
     CLEAN
    -0.06
    .JsonIgnore
    -0.06
    valuation
    -0.06
     smashed
    -0.06
    pl
    -0.06
     Behavioral
    -0.06
    .relative
    -0.06
    POSITIVE LOGITS
     leicht
    0.07
     розта
    0.07
     pouco
    0.07
    SSERT
    0.06
     والم
    0.06
    дром
    0.06
    BOOLE
    0.06
    КТ
    0.06
     вспом
    0.06
    xee
    0.06
    Act Density 0.008%

    No Known Activations