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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summed
    -0.06
    definition
    -0.06
     RV
    -0.06
    елей
    -0.06
     distingu
    -0.06
    랜드
    -0.06
     although
    -0.06
     strang
    -0.05
     rant
    -0.05
     Econom
    -0.05
    POSITIVE LOGITS
     "<?
    0.08
    :@"%@",
    0.07
    _FORM
    0.06
    >".$
    0.06
     равно
    0.06
    (True
    0.06
     chick
    0.06
    _Result
    0.06
    矢
    0.06
    atro
    0.06
    Act Density 0.001%

    No Known Activations