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

    Neuronpedia

    INDEX
    Explanations

    social and biological topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🄰
    0.45
     admits
    0.41
    aimana
    0.40
     নেতাকর্ম
    0.39
    Ꮢ
    0.38
    fila
    0.38
    ÁS
    0.38
    ými
    0.38
     depriving
    0.38
    ாம
    0.38
    POSITIVE LOGITS
    wonder
    0.40
    href
    0.38
    どうぞ
    0.37
     Assistants
    0.37
     демонстра
    0.37
    channels
    0.36
    信任
    0.36
     wonder
    0.35
    isle
    0.35
    keys
    0.35
    Act Density 0.000%

    No Known Activations