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
    .ContextCompat
    -0.07
    lj
    -0.07
    สร
    -0.07
    estival
    -0.07
    �
    -0.07
     pope
    -0.06
     persecution
    -0.06
     الكتاب
    -0.06
     thi
    -0.06
    十四
    -0.06
    POSITIVE LOGITS
    (clean
    0.07
    :'',
    0.06
    雷
    0.06
    730
    0.06
    ADIO
    0.06
     اش
    0.06
    _subplot
    0.06
    $")↵
    0.06
     βο
    0.06
     кли
    0.06
    Act Density 0.050%

    No Known Activations