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

    Neuronpedia

    INDEX
    Explanations

    various topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (build
    -0.08
    “그
    -0.07
     backtrack
    -0.07
    .packet
    -0.07
    -build
    -0.07
    委员会
    -0.06
    erd
    -0.06
    раниц
    -0.06
    -write
    -0.06
    (...)↵
    -0.06
    POSITIVE LOGITS
     via
    0.06
     WITHOUT
    0.06
    adoras
    0.06
     должно
    0.06
    deo
    0.06
    Styles
    0.06
    ่าอ
    0.06
     información
    0.06
     decis
    0.06
    .DataGridViewTriState
    0.06
    Act Density 0.038%

    No Known Activations