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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hash
    -0.07
     disciplines
    -0.07
    INNER
    -0.07
     abound
    -0.07
    Ending
    -0.07
     currencies
    -0.07
    _merge
    -0.07
    ín
    -0.07
     clever
    -0.07
    沈
    -0.07
    POSITIVE LOGITS
    188
    0.09
    194
    0.08
    186
    0.08
    ۱۹۴
    0.08
    201
    0.07
    200
    0.07
    ۱۹۹
    0.07
    ۱۹۸
    0.07
    199
    0.07
    187
    0.07
    Act Density 0.051%

    No Known Activations