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

    Neuronpedia

    INDEX
    Explanations

    asking about causes or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    一枚
    0.39
    胞
    0.37
    =$\
    0.36
    kingdom
    0.35
     forgiven
    0.35
    ंडे
    0.34
     Möglichkeit
    0.34
     विजिट
    0.34
     poquito
    0.33
    សារ
    0.33
    POSITIVE LOGITS
    ヘ
    0.44
     हेयर
    0.43
     Gera
    0.43
     காரணம்
    0.42
     hé
    0.42
    чора
    0.41
     헤
    0.41
     اللون
    0.40
     radiating
    0.40
     ஹெ
    0.40
    Act Density 0.000%

    No Known Activations