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

    Neuronpedia

    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ในช
    -0.07
    575
    -0.06
     dubna
    -0.06
     aver
    -0.06
    �
    -0.06
    卡
    -0.06
     Astr
    -0.06
     otra
    -0.06
     Para
    -0.05
    lanır
    -0.05
    POSITIVE LOGITS
     
    0.08
    ень
    0.08
    _Up
    0.08
    �
    0.08
    h
    0.07
    лон
    0.07
     мот
    0.07
    он
    0.07
    vm
    0.07
    му
    0.07
    Act Density 0.269%

    No Known Activations