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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hunts
    -0.07
    enes
    -0.07
    fork
    -0.07
    ращ
    -0.07
    Dimensions
    -0.07
    Rh
    -0.07
     Schools
    -0.06
     cause
    -0.06
     propre
    -0.06
     arbitrarily
    -0.06
    POSITIVE LOGITS
     RESP
    0.06
    FIN
    0.06
    ..<
    0.06
     amacıyla
    0.06
    ATAB
    0.06
    ElapsedTime
    0.05
    refixer
    0.05
    TAB
    0.05
     UB
    0.05
    [['
    0.05
    Act Density 0.064%

    No Known Activations