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

    Neuronpedia

    INDEX
    Explanations

    conflicts and historical events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	widget
    -0.07
     коллек
    -0.07
    _Begin
    -0.07
    艺术
    -0.06
    andler
    -0.06
     Prototype
    -0.06
    rotate
    -0.06
     Calibration
    -0.06
     Mash
    -0.06
    Practice
    -0.06
    POSITIVE LOGITS
    etheus
    0.07
    <source
    0.07
    MATCH
    0.07
     websocket
    0.06
    ůst
    0.06
    .switch
    0.06
     derive
    0.06
     memorable
    0.06
     haute
    0.06
    nowrap
    0.06
    Act Density 0.032%

    No Known Activations