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

    Neuronpedia

    INDEX
    Explanations

    namedtuple

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dried
    -0.07
    sole
    -0.07
    새
    -0.07
    .cols
    -0.06
     Salv
    -0.06
    дов
    -0.06
    白色
    -0.06
    ;o
    -0.06
    露天
    -0.06
     Tap
    -0.06
    POSITIVE LOGITS
    hetics
    0.07
    赟
    0.07
    名誉
    0.07
     reports
    0.06
    REDIT
    0.06
    ]-$
    0.06
    вшего
    0.06
    )],↵
    0.06
    _DISABLE
    0.06
    Nobody
    0.06
    Act Density 0.002%

    No Known Activations