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

    Neuronpedia

    INDEX
    Explanations

    hierarchical data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ade
    0.45
    away
    0.45
    ari
    0.45
    hen
    0.43
    arium
    0.43
    erv
    0.42
    ere
    0.41
    io
    0.41
    ann
    0.41
    érien
    0.40
    POSITIVE LOGITS
    ..”
    0.44
     texas
    0.42
     groupby
    0.42
    NCIA
    0.42
     ഭാഗ
    0.41
    贿
    0.40
     వ్యక్
    0.39
    鄀
    0.39
    ญิง
    0.38
     విభ
    0.38
    Act Density 0.001%

    No Known Activations