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

    Neuronpedia

    INDEX
    Explanations

    finding or locating things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    0.95
    ఛ
    0.95
     pripre
    0.89
     mattered
    0.88
     demean
    0.85
    নিষ
    0.84
     scolaire
    0.83
    ır
    0.82
    डे
    0.81
     razum
    0.81
    POSITIVE LOGITS
    toggle
    1.00
     correlations
    0.97
     lurking
    0.93
    뵙
    0.93
     prevalence
    0.93
    找到
    0.89
     convince
    0.88
     knack
    0.87
    เจอ
    0.87
    arounds
    0.87
    Act Density 0.345%

    No Known Activations