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

    Neuronpedia

    INDEX
    Explanations

    health cautions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _encoder
    -0.07
     ALPHA
    -0.07
    Lazy
    -0.07
    Videos
    -0.06
    <n
    -0.06
    JWT
    -0.06
    -American
    -0.06
     containers
    -0.06
     joking
    -0.06
    _routing
    -0.06
    POSITIVE LOGITS
     přech
    0.06
     ecc
    0.06
     aktual
    0.06
    uffer
    0.06
     escorted
    0.05
    {$
    0.05
    oolStrip
    0.05
     duż
    0.05
     DISPLAY
    0.05
     HAPP
    0.05
    Act Density 0.051%

    No Known Activations