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

    Neuronpedia

    INDEX
    Explanations

    `\log`, `free license`, `bruises`, `query`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     અપ
    0.38
     przyj
    0.36
     krzy
    0.36
    후
    0.35
    ВА
    0.34
    꺼
    0.34
    }}(
    0.33
    raj
    0.33
    kk
    0.33
     دي
    0.32
    POSITIVE LOGITS
    medel
    0.42
     invitation
    0.41
     Invitation
    0.41
    根
    0.41
    硖
    0.41
     unbeaten
    0.40
    uspended
    0.39
     मद्देनजर
    0.39
     paragra
    0.39
    мена
    0.39
    Act Density 0.053%

    No Known Activations