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

    Neuronpedia

    INDEX
    Explanations

    deep learning terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ult
    -0.06
    -var
    -0.06
    Cla
    -0.06
    -0.06
     buttons
    -0.06
     Fifth
    -0.06
     元
    -0.06
     sex
    -0.06
     Pun
    -0.06
    脸
    -0.06
    POSITIVE LOGITS
    .ForeColor
    0.07
    (FLAGS
    0.07
     samostat
    0.07
    .softmax
    0.06
    _FW
    0.06
    .***.***
    0.06
    modity
    0.06
    etSocketAddress
    0.06
    _mr
    0.06
    _CONTROLLER
    0.06
    Act Density 0.063%

    No Known Activations