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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotic
    -0.08
     یک
    -0.07
    丘
    -0.07
    wjgl
    -0.07
    书记
    -0.07
    浴
    -0.07
    .vertical
    -0.07
    HttpClient
    -0.07
    到底
    -0.06
    .Login
    -0.06
    POSITIVE LOGITS
    (rand
    0.06
    (',
    0.06
     gift
    0.06
    .tie
    0.06
     
↵ 
↵
    0.06
     dif
    0.06
     Charleston
    0.06
    lad
    0.06
     mourn
    0.06
     vox
    0.06
    Act Density 0.062%

    No Known Activations