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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usuario
    -0.06
    …but
    -0.06
     قبل
    -0.06
    [property
    -0.06
    attack
    -0.06
     adicion
    -0.06
     Wife
    -0.06
    _rad
    -0.06
    xes
    -0.06
    .Settings
    -0.06
    POSITIVE LOGITS
    英文
    0.07
    긴
    0.07
    дая
    0.07
    货
    0.06
    における
    0.06
     kultur
    0.06
     조선
    0.06
     IDD
    0.06
    گ
    0.06
    ับน
    0.06
    Act Density 0.035%

    No Known Activations