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

    Neuronpedia

    INDEX
    Explanations

    AI chatbot disclaimers mental health violence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unfolded
    0.74
     depositphotos
    0.70
     சாப்பிட
    0.69
     undec
    0.68
    unia
    0.65
     පො
    0.65
     zet
    0.64
     გახ
    0.64
     clap
    0.64
     ചെയ
    0.63
    POSITIVE LOGITS
    Repl
    0.61
    人的
    0.60
    ắt
    0.56
     র
    0.55
    LAM
    0.54
     Ble
    0.54
     Severe
    0.54
    Ｖ
    0.54
    SA
    0.53
    Re
    0.53
    Act Density 0.156%

    No Known Activations