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

    Neuronpedia

    INDEX
    Explanations

    word beginnings across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     berkaitan
    0.26
    0
    0.25
    Of
    0.25
    vol
    0.25
    cl
    0.25
    _
    0.24
    cat
    0.23
    fc
    0.23
    ased
    0.23
    cap
    0.23
    POSITIVE LOGITS
    ک
    0.33
     royaume
    0.29
     popolo
    0.28
     Conselho
    0.28
     esfuer
    0.28
     Musik
    0.27
    મ
    0.27
     thème
    0.26
    morrow
    0.26
    ش
    0.26
    Act Density 0.054%

    No Known Activations