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

    Neuronpedia

    INDEX
    Explanations

    unable to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಮಾಡಿದ್ದಾರೆ
    0.37
    SIE
    0.34
    ίσ
    0.33
     SIE
    0.33
    ︿
    0.31
     weapons
    0.31
    LIKE
    0.31
    GUND
    0.30
     Mutation
    0.30
     encontrada
    0.30
    POSITIVE LOGITS
    tan
    0.36
    เอก
    0.36
     pariy
    0.35
     benefitting
    0.35
    бавля
    0.35
    サーバ
    0.34
    дж
    0.33
    ank
    0.33
    かけて
    0.32
    selValue
    0.31
    Act Density 0.024%

    No Known Activations