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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _compress
    -0.07
     IEnumerator
    -0.07
     separators
    -0.07
    免费
    -0.06
    Copy
    -0.06
    év
    -0.06
     workers
    -0.06
    št
    -0.06
     Exc
    -0.06
    _voltage
    -0.06
    POSITIVE LOGITS
     figure
    0.07
    となり
    0.06
     túi
    0.06
     Humanity
    0.06
     fostering
    0.06
    WARNING
    0.05
     최근
    0.05
     douche
    0.05
     worm
    0.05
     discard
    0.05
    Act Density 0.154%

    No Known Activations