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

    Neuronpedia

    INDEX
    Explanations

    Foreign names/places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fraction
    -0.07
    endsWith
    -0.06
     Hai
    -0.06
     investigación
    -0.06
    emble
    -0.06
    ुड
    -0.06
    ерату
    -0.06
     myfile
    -0.06
    ovo
    -0.06
    ीएस
    -0.06
    POSITIVE LOGITS
     olanak
    0.07
    ैय
    0.07
    결
    0.06
    Columns
    0.06
     societal
    0.06
     держ
    0.06
    。',↵
    0.06
    apping
    0.06
     Contributions
    0.06
     अख
    0.06
    Act Density 0.036%

    No Known Activations