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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FileInputStream
    -0.57
    UrlResolution
    -0.56
     defStyle
    -0.55
     strand
    -0.48
     pool
    -0.48
    InvalidProtocol
    -0.47
     battery
    -0.47
     lung
    -0.47
     digital
    -0.46
     cu
    -0.46
    POSITIVE LOGITS
     Jefus
    0.75
     Socrates
    0.71
     يتيمه
    0.70
    ſelves
    0.66
     Sopho
    0.64
     Shakspeare
    0.64
     mijne
    0.64
    TypedDataSet
    0.63
    Diweddarwch
    0.63
     Chriftian
    0.63
    Act Density 0.026%

    No Known Activations