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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blackColor
    -0.06
     friendship
    -0.06
     Parents
    -0.06
     siz
    -0.06
    .FirstOrDefault
    -0.06
     But
    -0.06
     However
    -0.06
     uprising
    -0.06
     Likewise
    -0.06
     ay
    -0.06
    POSITIVE LOGITS
    ]'
    0.08
    accept
    0.07
    eyed
    0.07
     �
    0.06
     différents
    0.06
    assignments
    0.06
    redict
    0.06
    .getBody
    0.06
    است
    0.06
     muschi
    0.06
    Act Density 0.124%

    No Known Activations