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

    Neuronpedia

    INDEX
    Explanations

    Vehicle parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帝
    -0.08
    岁的
    -0.08
     ei
    -0.07
    Lady
    -0.07
    ☾
    -0.07
    掐
    -0.07
    先是
    -0.07
    sheets
    -0.07
    .every
    -0.07
    凰
    -0.07
    POSITIVE LOGITS
    Environment
    0.08
     bump
    0.07
    на
    0.07
    Resistance
    0.07
    ;br
    0.07
     collections
    0.06
    ประเภท
    0.06
    mid
    0.06
    grad
    0.06
    Orden
    0.06
    Act Density 0.107%

    No Known Activations