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

    Neuronpedia

    INDEX
    Explanations

    Internet forums and Usenet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Observers
    -0.07
     denounced
    -0.07
     receptions
    -0.06
     setInterval
    -0.06
    --------↵↵
    -0.06
    Statement
    -0.06
     spanking
    -0.06
    417
    -0.06
    ']↵
    -0.06
    _INSTALL
    -0.06
    POSITIVE LOGITS
    ератор
    0.07
    orde
    0.07
    canvas
    0.07
    าง
    0.06
    erdem
    0.06
     هتل
    0.06
     مشخص
    0.06
     belongings
    0.06
     başarılı
    0.06
    ومی
    0.06
    Act Density 0.020%

    No Known Activations