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

    Neuronpedia

    INDEX
    Explanations

    mat

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     says
    -0.07
    WG
    -0.07
     Principles
    -0.07
    '',
    -0.06
     lick
    -0.06
    (m
    -0.06
     пло
    -0.06
    Gun
    -0.06
     theorem
    -0.06
    //#
    -0.06
    POSITIVE LOGITS
    WINDOWS
    0.07
    .CreateIndex
    0.06
    	real
    0.06
    姓名
    0.06
    -xs
    0.06
    ){
↵
↵
    0.06
    _Stop
    0.06
     accel
    0.06
     відк
    0.06
     Mattis
    0.06
    Act Density 0.002%

    No Known Activations