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

    Neuronpedia

    INDEX
    Explanations

    instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Zap
    -0.07
     webs
    -0.06
     enr
    -0.06
     Ок
    -0.06
    egrity
    -0.06
    (verbose
    -0.06
     OK
    -0.06
    fik
    -0.06
     EditorGUI
    -0.06
    ۲۴
    -0.06
    POSITIVE LOGITS
    Instance
    0.13
    instance
    0.10
     Instance
    0.10
     Instances
    0.08
    .getInstance
    0.08
    newInstance
    0.08
    _inst
    0.08
    	instance
    0.08
    .instance
    0.08
    (instance
    0.08
    Act Density 0.009%

    No Known Activations