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

    Neuronpedia

    INDEX
    Explanations

    rate at which

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.79
    ored
    0.76
    ij
    0.73
    azione
    0.71
    iamo
    0.69
     senaste
    0.69
    owal
    0.68
    del
    0.67
    mission
    0.67
    olt
    0.67
    POSITIVE LOGITS
    ೇಳ
    0.86
     quilts
    0.84
     addons
    0.83
     мл
    0.83
     начинается
    0.83
     accumulates
    0.81
     clearInterval
    0.81
     getNode
    0.81
    мани
    0.80
     Mbps
    0.80
    Act Density 0.000%

    No Known Activations