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

    Neuronpedia

    INDEX
    Explanations

    ++

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wohnung
    -0.07
    _ROUTE
    -0.07
     affordable
    -0.06
     схем
    -0.06
    _socket
    -0.06
    _MESSAGE
    -0.06
    _handler
    -0.06
     FW
    -0.06
    수의
    -0.06
     tudo
    -0.06
    POSITIVE LOGITS
    ++;↵
    0.08
    +len
    0.08
     perv
    0.07
     ++;↵
    0.07
    ]++;↵
    0.07
    ++;↵↵
    0.07
    .chomp
    0.06
     fearless
    0.06
     SignUp
    0.06
     Şah
    0.06
    Act Density 0.006%

    No Known Activations