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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ประเทศไทย
    -0.07
     çift
    -0.07
     Мар
    -0.06
     CPL
    -0.06
    multiply
    -0.06
     Maint
    -0.06
    .Uri
    -0.06
    	Initialize
    -0.06
     CDC
    -0.06
     RL
    -0.06
    POSITIVE LOGITS
    :red
    0.07
     �
    0.06
    _RED
    0.06
     investig
    0.06
    orig
    0.06
     sigu
    0.06
    !!
    0.06
     концентра
    0.06
     ([[
    0.06
    IRM
    0.06
    Act Density 0.114%

    No Known Activations