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

    Neuronpedia

    INDEX
    Explanations

    placeholders like [Your Name]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doesn
    1.43
     isn
    1.34
    ský
    1.28
     is
    1.24
    R
    1.24
     enables
    1.22
     defines
    1.20
    K
    1.20
    न
    1.20
    W
    1.18
    POSITIVE LOGITS
     Üniversitesi
    1.38
    .
    1.38
    十分に
    1.33
     Ancak
    1.27
    ING
    1.24
    Բ
    1.23
     Obwohl
    1.20
     Cualquier
    1.20
    ണിക്ക
    1.19
     khắp
    1.18
    Act Density 0.079%

    No Known Activations