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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divisible
    -0.09
    θρω
    -0.07
    ucken
    -0.07
     Kathryn
    -0.07
     norge
    -0.06
    rror
    -0.06
     KV
    -0.06
    ۱۹۹
    -0.06
    christ
    -0.06
     एस
    -0.06
    POSITIVE LOGITS
     licenses
    0.06
     interpretation
    0.06
     figures
    0.06
     voters
    0.06
     Requests
    0.06
     Fabric
    0.06
     CHAPTER
    0.06
    >/',
    0.06
     id
    0.06
    .preprocessing
    0.06
    Act Density 0.024%

    No Known Activations