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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rağmen
    -0.07
     resisted
    -0.07
     plav
    -0.06
    levance
    -0.06
     Does
    -0.06
    .client
    -0.06
     forwarded
    -0.06
    ')+
    -0.06
    .='
    -0.06
    -safe
    -0.06
    POSITIVE LOGITS
     []↵
    0.08
    Une
    0.07
    =[]↵
    0.07
     záp
    0.07
     '';↵
    0.07
    氏
    0.07
    勢
    0.06
    AnimationFrame
    0.06
     Accom
    0.06
     уход
    0.06
    Act Density 0.011%

    No Known Activations