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

    Neuronpedia

    INDEX
    Explanations

    Anthropic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Попис
    0.68
     Bxc
    0.67
    ко
    0.66
     optimality
    0.63
    ючи
    0.62
    ются
    0.62
     Хоро
    0.62
     áng
    0.60
     toman
    0.59
    caf
    0.58
    POSITIVE LOGITS
    서
    0.77
     somehow
    0.71
    mathbf
    0.71
    ে
    0.70
     людьми
    0.67
    mathrm
    0.67
    گاه
    0.66
    ν
    0.65
    ണ
    0.64
    orge
    0.63
    Act Density 0.004%

    No Known Activations