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

    Neuronpedia

    INDEX
    Explanations

    parse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formerly
    -0.08
     Prado
    -0.08
     genuinely
    -0.08
     Doh
    -0.07
     Fre
    -0.07
    ))));↵
    -0.07
     Fowler
    -0.07
    +"_
    -0.07
     Aten
    -0.07
     :"
    -0.07
    POSITIVE LOGITS
     formulate
    0.09
    nić
    0.09
    itzar
    0.09
    latex
    0.08
     punya
    0.08
     समस्या
    0.08
     zunächst
    0.08
     interpretar
    0.08
    問題
    0.08
     ಸಮಸ್ಯ
    0.08
    Act Density 0.032%

    No Known Activations