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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     transfers
    -0.07
     Mayer
    -0.07
     backward
    -0.06
     stark
    -0.06
     --------------------------------
    -0.06
     dump
    -0.06
     preds
    -0.06
    AGER
    -0.06
     Smart
    -0.06
    ager
    -0.06
    POSITIVE LOGITS
    .ActionEvent
    0.07
    Luke
    0.06
     привед
    0.06
    	border
    0.06
     espec
    0.06
    	HANDLE
    0.06
     Luke
    0.06
    _HANDLER
    0.06
    UIAlert
    0.06
     deltaTime
    0.06
    Act Density 0.077%

    No Known Activations