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

    Neuronpedia

    INDEX
    Explanations

    training data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.96
    v
    0.93
    m
    0.89
    f
    0.88
    and
    0.88
    b
    0.88
    w
    0.85
    as
    0.84
    u
    0.84
    ol
    0.81
    POSITIVE LOGITS
     νό
    0.90
     ADHD
    0.86
     PFAS
    0.82
     naughty
    0.81
     дода
    0.81
     Ajoutez
    0.78
     Ví
    0.77
     PCOS
    0.76
     norepinephrine
    0.75
     ví
    0.75
    Act Density 0.284%

    No Known Activations