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

    Neuronpedia

    INDEX
    Explanations

    abuse, bullying, or perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كري
    0.46
     réal
    0.45
    ية
    0.44
     المسا
    0.43
    jenja
    0.42
     Ilust
    0.42
    štění
    0.41
     Органи
    0.41
     GREEN
    0.40
     sklearn
    0.40
    POSITIVE LOGITS
    meld
    0.49
    ählte
    0.47
    lø
    0.47
    valor
    0.46
    aes
    0.46
    咊
    0.45
    ać
    0.45
     decays
    0.44
    ađ
    0.44
    ถี่
    0.44
    Act Density 0.001%

    No Known Activations