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

    Neuronpedia

    INDEX
    Explanations

    Lifeline: crisis contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meditations
    0.35
    Quiet
    0.33
    fns
    0.33
    ড়ান্ত
    0.32
    MAE
    0.31
    ሉም
    0.31
     perturbation
    0.31
     Quiet
    0.31
    Living
    0.30
    ensely
    0.30
    POSITIVE LOGITS
    サービス
    0.43
    ك
    0.41
     assure
    0.41
     tedesco
    0.40
     servizi
    0.39
     assures
    0.39
     callers
    0.39
    pla
    0.39
     și
    0.38
     및
    0.38
    Act Density 0.040%

    No Known Activations