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

    Neuronpedia

    INDEX
    Explanations

    blog post URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.71
    UserScript
    -0.55
    espan
    -0.52
    EndProject
    -0.49
    omości
    -0.48
    }]
    -0.48
     Validators
    -0.48
    Lähteet
    -0.47
    पया
    -0.46
     AppModule
    -0.46
    POSITIVE LOGITS
    EndContext
    0.59
     فريبيس
    0.54
    MergeFrom
    0.52
     EconPapers
    0.51
    ьаж
    0.50
    InvalidProtocol
    0.50
     ostavi
    0.49
     tantum
    0.49
    단
    0.49
     zc
    0.48
    Act Density 0.002%

    No Known Activations