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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dt
    -0.06
    IBC
    -0.06
     verifies
    -0.06
     Spiral
    -0.06
    null
    -0.06
    일본
    -0.06
    ↵
    -0.06
    gis
    -0.06
    ovaného
    -0.06
    річ
    -0.06
    POSITIVE LOGITS
     HEADER
    0.07
     vaz
    0.06
     brutal
    0.06
    вроп
    0.06
    arkers
    0.06
     distributing
    0.06
    更新
    0.06
    iskey
    0.06
    MU
    0.06
     aj
    0.06
    Act Density 0.015%

    No Known Activations