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

    Neuronpedia

    INDEX
    Explanations

    threats and negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Margins
    0.49
    學
    0.45
    Navigate
    0.44
    MOBILE
    0.44
    راب
    0.44
    Farmers
    0.44
    Optimize
    0.43
    سك
    0.43
     فرص
    0.43
    盞
    0.43
    POSITIVE LOGITS
     castration
    0.51
     effetto
    0.49
     efeitos
    0.49
     enraged
    0.48
     murdered
    0.47
     estrut
    0.47
     murder
    0.46
     nyata
    0.46
     shock
    0.45
     paralyzed
    0.45
    Act Density 0.003%

    No Known Activations