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

    Neuronpedia

    INDEX
    Explanations

    Mark

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ES
    0.73
     kie
    0.68
    浗
    0.66
     Territorial
    0.65
     ph
    0.64
    堰
    0.64
     c
    0.64
     Coliseum
    0.64
    ็ค
    0.63
     разно
    0.63
    POSITIVE LOGITS
    gers
    0.78
     चेन
    0.74
     charity
    0.71
    incision
    0.67
    horas
    0.66
    spanning
    0.65
    setcounter
    0.65
     Charity
    0.65
     ज्येष्ठ
    0.65
    延伸
    0.63
    Act Density 0.004%

    No Known Activations