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

    Neuronpedia

    INDEX
    Explanations

    Project retrospectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    digits
    -0.09
    -bearing
    -0.08
    oncé
    -0.08
     Soph
    -0.08
     digits
    -0.08
     polynomial
    -0.08
     பூ
    -0.08
    Polynomial
    -0.07
     licking
    -0.07
    Digits
    -0.07
    POSITIVE LOGITS
     successes
    0.11
     aprend
    0.10
    ，下
    0.09
     verbessert
    0.09
     улучш
    0.09
     identifica
    0.09
     tweaks
    0.09
     verbeter
    0.09
     learn
    0.09
     melhoria
    0.09
    Act Density 0.010%

    No Known Activations