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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    members
    -0.07
     Glass
    -0.07
    PRETTY
    -0.06
    	task
    -0.06
     fatally
    -0.06
     clear
    -0.06
    ourcing
    -0.06
    ESP
    -0.06
     premise
    -0.06
     Cher
    -0.06
    POSITIVE LOGITS
     ******************************************************************************↵
    0.06
    ,password
    0.06
    _AM
    0.06
    _logged
    0.06
    =Math
    0.06
    xfb
    0.06
    .directive
    0.06
    킬
    0.06
    -click
    0.06
    .omg
    0.06
    Act Density 0.001%

    No Known Activations