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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特种
    -0.07
    챘
    -0.07
    ValuePair
    -0.06
     pai
    -0.06
     hits
    -0.06
    应在
    -0.06
    virt
    -0.06
     -.
    -0.06
     unaffected
    -0.06
    utc
    -0.06
    POSITIVE LOGITS
    [size
    0.07
     bamboo
    0.07
    _empresa
    0.07
    .firestore
    0.07
    .Show
    0.07
     Murder
    0.06
    (orig
    0.06
    廠
    0.06
     textDecoration
    0.06
    ERGY
    0.06
    Act Density 0.060%

    No Known Activations