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

    Neuronpedia

    INDEX
    Explanations

    str or pathlib.Path

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     buts
    1.05
    Elli
    1.03
     classification
    1.00
     guesses
    0.99
     droits
    0.98
     accurate
    0.95
     sorte
    0.93
     precise
    0.93
     philosophie
    0.93
     rectum
    0.91
    POSITIVE LOGITS
    КИ
    1.13
    álen
    1.05
    ки
    1.02
    ک
    0.98
    前記
    0.94
     miał
    0.93
    ły
    0.93
    taş
    0.92
    烷
    0.91
     Realtor
    0.91
    Act Density 0.000%

    No Known Activations