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

    Neuronpedia

    INDEX
    Explanations

    biases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ヂストン
    0.41
     Añ
    0.40
     Win
    0.39
     cytoplasmic
    0.38
     გვ
    0.38
     opt
    0.37
     copie
    0.36
     botao
    0.36
     palsy
    0.36
     demanding
    0.35
    POSITIVE LOGITS
    ráf
    0.47
     некоторых
    0.45
     различных
    0.44
    icoli
    0.43
    众
    0.42
    Heute
    0.42
    din
    0.41
    truck
    0.41
    僌
    0.40
    resent
    0.40
    Act Density 0.013%

    No Known Activations