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

    Neuronpedia

    INDEX
    Explanations

    quoted statements attributed to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Suppose
    0.52
     imagining
    0.49
     if
    0.46
    Suppose
    0.45
     మీకు
    0.45
     If
    0.44
     you
    0.43
     אם
    0.42
     supposing
    0.42
     Vous
    0.41
    POSITIVE LOGITS
     ovviamente
    0.54
     evidentemente
    0.54
     évidemment
    0.53
    Obviously
    0.52
     obviously
    0.52
     obviamente
    0.52
    obviously
    0.48
     طبعا
    0.48
     Obviously
    0.44
     pihaknya
    0.44
    Act Density 0.005%

    No Known Activations