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

    Neuronpedia

    INDEX
    Explanations

    ongoing descriptions and strategies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.50
     on
    0.48
     from
    0.43
    ắ
    0.43
     first
    0.42
     of
    0.41
     probably
    0.41
     four
    0.40
     From
    0.40
    ete
    0.39
    POSITIVE LOGITS
     మరియు
    0.42
    🏭
    0.41
     आर्थिक
    0.40
    리와
    0.40
    Deposito
    0.40
    RELATIVA
    0.39
    quera
    0.39
    ំន
    0.38
     instytuc
    0.38
     ולה
    0.38
    Act Density 0.000%

    No Known Activations