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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     comed
    -0.07
     Strings
    -0.06
    _ENTER
    -0.06
     ;
↵
↵
    -0.06
     checkout
    -0.06
     quay
    -0.06
    _PUSH
    -0.06
    sea
    -0.06
    xFA
    -0.06
    ",-
    -0.06
    POSITIVE LOGITS
    .getAs
    0.06
    Either
    0.06
    优势
    0.06
     ']
    0.06
     getModel
    0.06
    icas
    0.06
     Gab
    0.06
    _sell
    0.06
    Elements
    0.06
    ární
    0.06
    Act Density 0.002%

    No Known Activations