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

    Neuronpedia

    INDEX
    Explanations

    raw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patrick
    -0.08
    券
    -0.07
     probabil
    -0.07
    >You
    -0.07
    Temporary
    -0.07
    ponential
    -0.07
     خلق
    -0.07
     initializes
    -0.06
     depot
    -0.06
     Benn
    -0.06
    POSITIVE LOGITS
    COMPLETE
    0.07
     شیر
    0.06
    すべて
    0.06
    _WH
    0.06
     anonymous
    0.06
    272
    0.06
     Discord
    0.06
     PANEL
    0.06
     OPT
    0.06
    ators
    0.05
    Act Density 0.013%

    No Known Activations