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

    Neuronpedia

    INDEX
    Explanations

    attitudes towards topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    0.91
    there
    0.79
    the
    0.77
     faça
    0.76
    warranty
    0.74
    tc
    0.73
    south
    0.72
     هناك
    0.72
    electrical
    0.71
    memory
    0.70
    POSITIVE LOGITS
    感情
    0.71
    顗
    0.70
    рт
    0.68
     of
    0.65
     attitudes
    0.65
    ст
    0.64
    一时
    0.64
     actitudes
    0.63
     críticas
    0.62
    }&\
    0.62
    Act Density 0.016%

    No Known Activations