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

    Neuronpedia

    INDEX
    Explanations

    patent application description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFile
    0.45
     deviate
    0.43
    ao
    0.42
    op
    0.42
    フト
    0.42
     Poisson
    0.42
     conquer
    0.41
     invincible
    0.41
     細胞
    0.41
    ísmo
    0.40
    POSITIVE LOGITS
    Delayed
    0.53
    された
    0.44
    았
    0.44
    Description
    0.42
    Agricultural
    0.42
    Decorative
    0.42
    dyž
    0.42
    Connection
    0.41
    Digest
    0.41
    Electro
    0.41
    Act Density 0.000%

    No Known Activations