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

    Neuronpedia

    INDEX
    Explanations

    deeds and rewards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urrenc
    -0.08
    .entries
    -0.07
     returnValue
    -0.07
    猛地
    -0.07
    항
    -0.07
    .prevent
    -0.07
    unist
    -0.07
    所提供的
    -0.07
     Cruiser
    -0.07
    幻想
    -0.07
    POSITIVE LOGITS
     Original
    0.07
     אוה
    0.07
     bloginfo
    0.07
     trụ
    0.07
    ұ
    0.07
     cush
    0.07
     promote
    0.06
    镵
    0.06
    敩
    0.06
     Creative
    0.06
    Act Density 0.004%

    No Known Activations