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

    Neuronpedia

    INDEX
    Explanations

    located

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     located
    -0.52
     taus
    -0.49
     diha
    -0.46
     lagen
    -0.45
     assis
    -0.44
     ―――――
    -0.44
     Reſ
    -0.43
    hax
    -0.42
     brz
    -0.41
     
    -0.41
    POSITIVE LOGITS
    uxxxx
    0.77
    олові
    0.65
    يكب
    0.64
    kannya
    0.60
     emplois
    0.59
     extérieurs
    0.59
     NSCoder
    0.58
    rungsseite
    0.57
    ondissement
    0.57
     @"/
    0.56
    Act Density 0.053%

    No Known Activations