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

    Neuronpedia

    INDEX
    Explanations

    parent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    配套
    -0.07
    𓈒
    -0.07
    没收
    -0.07
     help
    -0.06
    落实
    -0.06
    ㉣
    -0.06
    .Redirect
    -0.06
    Ϝ
    -0.06
    ǝ
    -0.06
     also
    -0.06
    POSITIVE LOGITS
    晟
    0.07
     attracting
    0.07
    Profit
    0.07
    _performance
    0.07
     tier
    0.07
    蓉
    0.07
    高的
    0.07
    昱
    0.07
    дрес
    0.06
     Layers
    0.06
    Act Density 0.000%

    No Known Activations