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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staffers
    -0.07
     presence
    -0.07
     Routing
    -0.06
     runs
    -0.06
    정보
    -0.06
     definitions
    -0.06
    _ack
    -0.06
     hashes
    -0.06
     shoulder
    -0.06
     workaround
    -0.06
    POSITIVE LOGITS
     ازدواج
    0.07
    ToolStrip
    0.07
     न
    0.07
     Зав
    0.06
    BILL
    0.06
    /popper
    0.06
     gute
    0.06
    -gnu
    0.06
     preferredStyle
    0.06
    ANCELED
    0.06
    Act Density 0.033%

    No Known Activations