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

    Neuronpedia

    INDEX
    Explanations

    application development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loginfo
    0.84
     فريبي
    0.81
     Schuster
    0.79
     SDW
    0.76
    Methoxy
    0.75
    tzmann
    0.75
     thiab
    0.74
     BLUENRG
    0.72
    ujte
    0.71
    LookAnd
    0.71
    POSITIVE LOGITS
    d
    0.79
    es
    0.78
     চীন
    0.70
    全球
    0.70
    用餐
    0.69
    确
    0.69
    の流れ
    0.66
    g
    0.65
    米
    0.65
    ^{
    0.64
    Act Density 0.002%

    No Known Activations