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
    破
    -0.07
    菇
    -0.07
    orpion
    -0.07
    Monkey
    -0.07
    摸
    -0.06
     Excellent
    -0.06
    .tv
    -0.06
    不错
    -0.06
    _closure
    -0.06
    青蛙
    -0.06
    POSITIVE LOGITS
    -transparent
    0.07
    _returns
    0.07
     stronghold
    0.07
    willReturn
    0.06
    싹
    0.06
    -----↵
    0.06
    �
    0.06
    ととも
    0.06
    äter
    0.06
    当我
    0.06
    Act Density 0.002%

    No Known Activations