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

    Neuronpedia

    INDEX
    Explanations

    list element separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fortune
    0.46
    Per
    0.42
     Per
    0.41
    TT
    0.41
    Find
    0.39
     Su
    0.39
    W
    0.39
     Self
    0.39
    Power
    0.39
    Su
    0.38
    POSITIVE LOGITS
    ɺ
    0.45
     kullanılan
    0.45
     raus
    0.42
     النسبيه
    0.41
    лянчук
    0.40
     dersimizde
    0.40
     rufo
    0.40
    ългар
    0.40
     dubbio
    0.39
     なかっ
    0.39
    Act Density 0.010%

    No Known Activations