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

    Neuronpedia

    INDEX
    Explanations

    file extensions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STORY
    -0.08
    _bg
    -0.07
     ERP
    -0.07
     फर
    -0.07
    說
    -0.06
    开奖
    -0.06
    报
    -0.06
     winter
    -0.06
     drone
    -0.06
    ikal
    -0.06
    POSITIVE LOGITS
    .H
    0.07
    .M
    0.07
    .S
    0.07
    .G
    0.07
    .N
    0.06
    .B
    0.06
    .C
    0.06
     лич
    0.06
    .T
    0.06
    bugs
    0.06
    Act Density 0.060%

    No Known Activations