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

    Neuronpedia

    INDEX
    Explanations

    say "fire" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bags
    -0.07
    leigh
    -0.07
     Erg
    -0.06
     charging
    -0.06
    Colour
    -0.06
     Charleston
    -0.06
     Dhabi
    -0.06
    _HIDDEN
    -0.06
    (Column
    -0.06
     som
    -0.06
    POSITIVE LOGITS
    ไป
    0.06
     운
    0.06
    μιλος
    0.06
    _RSA
    0.06
     functionName
    0.06
    count
    0.06
     Nights
    0.06
     Teams
    0.06
    (Json
    0.06
     timings
    0.06
    Act Density 0.080%

    No Known Activations