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

    Neuronpedia

    INDEX
    Explanations

    business/tech news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    samples
    -0.07
    友好
    -0.07
    焊
    -0.07
     initiation
    -0.07
    왑
    -0.06
     unidades
    -0.06
    깹
    -0.06
     imagery
    -0.06
    射
    -0.06
    ",@"
    -0.06
    POSITIVE LOGITS
    UNDER
    0.07
    .V
    0.07
    [H
    0.07
     cog
    0.07
    func
    0.07
    “This
    0.07
    usz
    0.07
     contextual
    0.06
    istung
    0.06
    ptime
    0.06
    Act Density 0.169%

    No Known Activations