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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    />↵↵
    -0.06
    くな
    -0.06
    ěli
    -0.06
    <KeyValuePair
    -0.06
     حذف
    -0.06
    .Send
    -0.06
    _()↵
    -0.06
     Marion
    -0.06
    وذ
    -0.06
     dzi
    -0.06
    POSITIVE LOGITS
    ,+
    0.06
    IFICATION
    0.06
     Pun
    0.06
    rende
    0.06
     Injury
    0.06
    ард
    0.06
    ап
    0.06
    ीन
    0.06
    _utf
    0.06
     Call
    0.06
    Act Density 0.017%

    No Known Activations