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

    Neuronpedia

    INDEX
    Explanations

    special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тол
    -0.08
     lâu
    -0.07
     πριν
    -0.07
     toen
    -0.07
     посл
    -0.07
     ورود
    -0.06
     požad
    -0.06
     پایان
    -0.06
    codigo
    -0.06
     місця
    -0.06
    POSITIVE LOGITS
     الوط
    0.07
    Eth
    0.06
    _break
    0.06
    /Desktop
    0.06
    ैं.
    0.06
    علومات
    0.06
    shutdown
    0.06
    озд
    0.06
    !..
    0.06
     :
    0.06
    Act Density 0.120%

    No Known Activations