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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (SP
    -0.07
    (real
    -0.07
    .load
    -0.07
    蛋
    -0.07
     گ
    -0.07
    essler
    -0.06
     sheet
    -0.06
    宮
    -0.06
    alternative
    -0.06
     Wellness
    -0.06
    POSITIVE LOGITS
     FileInputStream
    0.06
    _DECLS
    0.06
     kissing
    0.06
     CIA
    0.06
     Ars
    0.06
     Agricultural
    0.06
     {
↵
↵
    0.06
    deme
    0.06
     jasmine
    0.06
    	then
    0.06
    Act Density 0.004%

    No Known Activations