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

    Neuronpedia

    INDEX
    Explanations

    aside

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     power
    -0.08
    ัตร
    -0.08
     growth
    -0.07
     Health
    -0.07
    (path
    -0.07
    pectral
    -0.07
    demand
    -0.07
     commanded
    -0.07
    height
    -0.07
     romant
    -0.07
    POSITIVE LOGITS
     aside
    0.11
     sake
    0.07
     Chí
    0.07
     Aside
    0.07
    Aside
    0.07
     آی
    0.07
    lož
    0.07
    伏
    0.07
    _holder
    0.07
     Leslie
    0.06
    Act Density 0.003%

    No Known Activations