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

    Neuronpedia

    INDEX
    Explanations

    PostgreSQL commands (`\d`, `\l`)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Probability
    0.42
    probability
    0.39
    ivasena
    0.38
    Chemical
    0.38
     probability
    0.38
    贈
    0.38
    Py
    0.37
    probabilities
    0.37
    Pyrid
    0.37
    isAssignableFrom
    0.37
    POSITIVE LOGITS
     ।*
    0.54
    pard
    0.50
    aspetto
    0.44
     w
    0.44
     pross
    0.43
     aspetto
    0.42
     (\
    0.41
     dib
    0.41
     meta
    0.41
    ಹ
    0.40
    Act Density 0.003%

    No Known Activations