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

    Neuronpedia

    INDEX
    Explanations

    roleplay

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    C
    1.61
    ности
    1.53
    I
    1.53
    M
    1.52
    Y
    1.48
    J
    1.44
     similaires
    1.37
    T
    1.35
    вим
    1.34
    B
    1.30
    POSITIVE LOGITS
    '
    1.66
    tered
    1.55
    tering
    1.47
    .
    1.38
     Farms
    1.34
     Suprem
    1.34
    ters
    1.32
     toad
    1.29
     chickpeas
    1.29
     microtubules
    1.29
    Act Density 0.074%

    No Known Activations