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

    Neuronpedia

    INDEX
    Explanations

    common explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     opposit
    0.87
     Pochettino
    0.76
    嘴角
    0.75
     propagates
    0.75
     accumulates
    0.74
     Weyl
    0.74
     embell
    0.73
     mutter
    0.72
     Toner
    0.71
     overwhel
    0.71
    POSITIVE LOGITS
    üş
    0.86
    čių
    0.80
    ście
    0.74
    ys
    0.74
    ład
    0.73
    ות
    0.72
    ło
    0.70
    eee
    0.70
    нические
    0.70
    d
    0.70
    Act Density 0.001%

    No Known Activations