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

    Neuronpedia

    INDEX
    Explanations

    patent application date

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necessity
    0.49
    iotsitewise
    0.46
     necesidad
    0.45
     cardi
    0.44
    ラク
    0.43
    ceu
    0.43
    assapi
    0.42
     cannabin
    0.42
    uszt
    0.41
     capit
    0.40
    POSITIVE LOGITS
     Descriptions
    0.50
     merasakan
    0.43
    .}$
    0.42
    仲
    0.41
    ्व
    0.40
     विचार
    0.40
    וע
    0.40
     Residual
    0.40
     系列
    0.40
    厌
    0.40
    Act Density 0.003%

    No Known Activations