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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conversion
    -0.06
    ]),↵
    -0.06
     disclosed
    -0.06
    .*)
    -0.06
    argv
    -0.06
    whole
    -0.06
    Keywords
    -0.06
     Johannesburg
    -0.06
    ACITY
    -0.06
    Degrees
    -0.06
    POSITIVE LOGITS
     sağlan
    0.07
    undry
    0.07
     süt
    0.07
     listening
    0.07
    озможно
    0.07
    usahaan
    0.06
    uzu
    0.06
    gz
    0.06
     herk
    0.06
     underestimated
    0.06
    Act Density 0.063%

    No Known Activations