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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stdafx
    -0.07
     nový
    -0.07
    =t
    -0.07
     ""){↵
    -0.07
    umer
    -0.07
     svém
    -0.07
     nás
    -0.07
     mein
    -0.06
    ayacak
    -0.06
    ();)
    -0.06
    POSITIVE LOGITS
    TokenType
    0.06
     کاربران
    0.06
     plutôt
    0.06
     tcb
    0.06
    ادث
    0.06
    Usage
    0.06
    _socket
    0.06
     binaries
    0.06
     технолог
    0.06
     scanning
    0.06
    Act Density 0.069%

    No Known Activations