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

    Neuronpedia

    INDEX
    Explanations

    domestic violence support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шек
    0.68
     Ruff
    0.67
    ecuzione
    0.65
    ष्क
    0.64
     RH
    0.63
     drawings
    0.62
     actively
    0.61
     py
    0.61
    ड्रन
    0.60
    ushka
    0.60
    POSITIVE LOGITS
     glass
    0.70
     Tall
    0.67
     Fold
    0.67
     Glass
    0.66
     biotic
    0.66
    Tall
    0.66
    Glass
    0.65
     tall
    0.62
    VT
    0.61
    ヴァ
    0.61
    Act Density 0.128%

    No Known Activations