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

    Neuronpedia

    INDEX
    Explanations

    related to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aggiunto
    0.46
     따르면
    0.41
     baseado
    0.39
    uş
    0.38
     Lizard
    0.38
    亮点
    0.38
    メーカー
    0.38
    oodle
    0.37
     Manufacturer
    0.36
    伝統
    0.36
    POSITIVE LOGITS
     pertain
    0.88
     relate
    0.84
     relates
    0.80
    directly
    0.80
     directly
    0.79
    に関連
    0.76
    直接
    0.73
     berkaitan
    0.72
     관련된
    0.71
     pertains
    0.69
    Act Density 0.023%

    No Known Activations