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

    Neuronpedia

    INDEX
    Explanations

    Sam, San, Sang, Samp, Sama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enví
    -0.92
     in
    -0.89
    游戏亮点
    -0.85
    儀式
    -0.79
    などが
    -0.79
     WRIGHT
    -0.79
    游戏特色
    -0.78
     людям
    -0.77
     of
    -0.75
     solicita
    -0.75
    POSITIVE LOGITS
    RESEARCH
    0.96
    際には
    0.96
    際は
    0.96
     సం
    0.93
     userDao
    0.92
    ところに
    0.91
    CCER
    0.90
    umesc
    0.85
     zaterdag
    0.85
     সং
    0.83
    Act Density 0.004%

    No Known Activations