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

    Neuronpedia

    INDEX
    Explanations

    Similar or required options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    áp
    -0.08
     evoc
    -0.08
    じめ
    -0.07
    ardon
    -0.07
    ital
    -0.07
     adept
    -0.07
     gé
    -0.07
    outes
    -0.07
    thought
    -0.07
     pues
    -0.07
    POSITIVE LOGITS
     varsa
    0.11
     meestal
    0.11
     suele
    0.11
     proprietary
    0.11
     бывает
    0.11
     usually
    0.10
     suelen
    0.10
    厂家
    0.10
    通常
    0.10
     brukar
    0.09
    Act Density 0.134%

    No Known Activations