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

    Neuronpedia

    INDEX
    Explanations

    wracked, writhing, worried, written

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rare
    0.76
    arean
    0.74
    Rare
    0.73
     Rare
    0.71
    rare
    0.70
     Bree
    0.69
     drifts
    0.66
     equating
    0.65
    nucleon
    0.64
     pneum
    0.64
    POSITIVE LOGITS
    tten
    0.88
    ITING
    0.87
    ttemberg
    0.82
    ithin
    0.80
    ld
    0.79
    ześ
    0.78
    paround
    0.74
    シップ
    0.73
    nesday
    0.73
    lds
    0.72
    Act Density 0.020%

    No Known Activations