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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    psych
    0.46
    Atom
    0.45
    Attrition
    0.43
    destruction
    0.43
    scratch
    0.42
    Aid
    0.40
    Psych
    0.40
    Mann
    0.40
     destruction
    0.39
    faction
    0.39
    POSITIVE LOGITS
     bukan
    0.53
     dès
    0.52
     décrites
    0.49
     nécessite
    0.48
     rencana
    0.48
     منصوبہ
    0.48
    新年
    0.48
     غیر
    0.48
     Soho
    0.47
     Botanical
    0.47
    Act Density 0.005%

    No Known Activations