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

    Neuronpedia

    INDEX
    Explanations

    reduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aver
    -0.07
     [_
    -0.07
    PCI
    -0.07
    oval
    -0.07
    順
    -0.07
    Computed
    -0.06
    odd
    -0.06
     achieve
    -0.06
    $/
    -0.06
    롭
    -0.06
    POSITIVE LOGITS
     roommate
    0.07
    ⨍
    0.07
    .Toolkit
    0.06
    VELO
    0.06
    鸺
    0.06
    titleLabel
    0.06
    煦
    0.06
    制裁
    0.06
     rozpoczę
    0.06
     SCAN
    0.06
    Act Density 0.008%

    No Known Activations