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

    Neuronpedia

    INDEX
    Explanations

    abuse and harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सलाहकार
    0.46
     đẹp
    0.42
    ರಾ
    0.41
    หนด
    0.40
    สวย
    0.40
    isseurs
    0.39
    goatee
    0.39
    美女
    0.38
    🔖
    0.38
     एकदम
    0.38
    POSITIVE LOGITS
     h
    0.45
    راز
    0.41
     squeezed
    0.40
     terrified
    0.39
    stwo
    0.38
     tô
    0.38
     Lander
    0.38
     widowed
    0.38
     murdered
    0.38
     frightened
    0.38
    Act Density 0.008%

    No Known Activations