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

    Neuronpedia

    INDEX
    Explanations

    Blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     леч
    -0.07
    adors
    -0.06
    =u
    -0.06
     kavram
    -0.06
    arena
    -0.06
     erotica
    -0.06
    (Roles
    -0.06
     каф
    -0.06
    예
    -0.06
     jur
    -0.06
    POSITIVE LOGITS
    sizlik
    0.06
    ُوا
    0.06
     інститут
    0.06
    政治
    0.06
    Candidate
    0.06
     compilation
    0.06
     مقدار
    0.06
    'article
    0.06
    jspb
    0.05
    -Allow
    0.05
    Act Density 0.783%

    No Known Activations