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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ану
    -0.08
    ixture
    -0.07
    واه
    -0.07
     Hank
    -0.06
    .blue
    -0.06
    redentials
    -0.06
     OA
    -0.06
     Frank
    -0.06
    فران
    -0.06
    iri
    -0.06
    POSITIVE LOGITS
    /)↵
    0.06
     professionally
    0.06
    resume
    0.06
    消
    0.06
    .defineProperty
    0.06
    fahren
    0.06
     Paginator
    0.06
    日に
    0.06
     girdi
    0.05
    )
↵
↵
↵
    0.05
    Act Density 0.037%

    No Known Activations