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

    Neuronpedia

    INDEX
    Explanations

    option value, talk with, few questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.60
    In
    0.45
    •
    0.44
    ·
    0.42
     in
    0.42
     lat
    0.42
    Wel
    0.42
    IB
    0.40
    "
    0.40
     Latin
    0.40
    POSITIVE LOGITS
    ěji
    0.54
    ீரி
    0.52
     शॉपिंग
    0.50
    utum
    0.49
     massless
    0.49
     किफायती
    0.49
     уя
    0.49
     hilarious
    0.48
    廰
    0.48
    amist
    0.47
    Act Density 0.000%

    No Known Activations