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

    Neuronpedia

    INDEX
    Explanations

    User-Agent strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uneven
    -0.08
    .Count
    -0.08
     Público
    -0.07
     Toledo
    -0.07
     cerebral
    -0.07
     clearfix
    -0.07
     Volvo
    -0.07
    angepicker
    -0.07
     رئيس
    -0.07
    钹
    -0.07
    POSITIVE LOGITS
    REDIT
    0.08
     müssen
    0.07
    ഷ
    0.07
                    ↵↵
    0.07
    iren
    0.07
    hex
    0.06
    DM
    0.06
    下行
    0.06
    hot
    0.06
     hym
    0.06
    Act Density 0.004%

    No Known Activations