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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]");↵
    -0.07
     стад
    -0.07
     parasite
    -0.07
     отправ
    -0.06
     credential
    -0.06
     bloginfo
    -0.06
    _TO
    -0.06
    Rom
    -0.06
    abilece
    -0.06
     عالية
    -0.06
    POSITIVE LOGITS
     os
    0.06
     linguistic
    0.06
    sembl
    0.06
     rose
    0.06
    ertainty
    0.06
     ninety
    0.06
    框
    0.06
     gram
    0.06
     approximate
    0.06
     mount
    0.06
    Act Density 0.007%

    No Known Activations