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

    Neuronpedia

    INDEX
    Explanations

    examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.51
     său
    0.50
     Einkauf
    0.49
     chegou
    0.49
     passou
    0.48
     événements
    0.47
     \%)$.
    0.46
     bột
    0.45
    CHAN
    0.45
     ধরণের
    0.45
    POSITIVE LOGITS
    incare
    0.47
    ia
    0.46
    estad
    0.46
    ership
    0.46
    motions
    0.45
    en
    0.45
    racht
    0.43
     했을
    0.43
    ivirus
    0.43
    ించు
    0.42
    Act Density 0.001%

    No Known Activations