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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    标准
    -0.07
     Cat
    -0.07
    _nome
    -0.07
    船舶
    -0.07
     eggs
    -0.07
    逻辑
    -0.07
    .desc
    -0.07
     설명
    -0.07
     Preston
    -0.07
    -row
    -0.07
    POSITIVE LOGITS
    (Tile
    0.07
    _DAMAGE
    0.07
    _past
    0.07
    (pow
    0.07
    .RESET
    0.07
     specialist
    0.07
    �
    0.07
     perplex
    0.06
    xDD
    0.06
    _patterns
    0.06
    Act Density 0.050%

    No Known Activations