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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++
    -0.08
    �ប
    -0.08
     cientí
    -0.08
     scientific
    -0.08
     code
    -0.08
     gourmet
    -0.08
    Scientific
    -0.08
     complète
    -0.07
    Numeric
    -0.07
     suite
    -0.07
    POSITIVE LOGITS
     gcd
    0.10
     marginalized
    0.09
     prerequisites
    0.08
     कमजोर
    0.08
     weakening
    0.08
     Shared
    0.08
     weakened
    0.08
     Einschr
    0.08
     waz
    0.08
     weaker
    0.08
    Act Density 0.012%

    No Known Activations