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

    Neuronpedia

    INDEX
    Explanations

    understanding diverse information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ethe
    0.95
    many
    0.95
    the
    0.86
     many
    0.82
    ede
    0.81
    museum
    0.81
    place
    0.77
     exacerbated
    0.76
    kr
    0.76
    muse
    0.75
    POSITIVE LOGITS
     Literary
    0.75
     NJ
    0.71
     гор
    0.70
    登
    0.67
    ছি
    0.66
     Shopping
    0.65
     Banking
    0.65
    वीं
    0.65
     服务
    0.65
     سر
    0.64
    Act Density 0.000%

    No Known Activations