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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    면적
    -0.08
    ningar
    -0.08
    ategory
    -0.07
    afort
    -0.07
    omik
    -0.07
    /master
    -0.07
    amak
    -0.06
    人才
    -0.06
    .correct
    -0.06
     strdup
    -0.06
    POSITIVE LOGITS
     ARGS
    0.07
    にお
    0.06
     indifference
    0.06
     intimately
    0.06
    experimental
    0.06
    /power
    0.06
     })↵↵↵
    0.06
     Operations
    0.06
    (delay
    0.06
    <>();↵
    0.06
    Act Density 0.001%

    No Known Activations