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

    Neuronpedia

    INDEX
    Explanations

    imidazolines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ============================================================================↵
    -0.07
     말을
    -0.07
    考え
    -0.07
     прави
    -0.07
    只是
    -0.07
    ��
    -0.07
     зни
    -0.07
     чист
    -0.07
     occas
    -0.07
     مهم
    -0.07
    POSITIVE LOGITS
     кал
    0.06
     Hal
    0.06
     Τα
    0.06
    database
    0.06
    .RES
    0.06
     Basketball
    0.06
    isActive
    0.06
    γγελ
    0.06
    AZ
    0.06
    allows
    0.06
    Act Density 0.002%

    No Known Activations