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

    Neuronpedia

    INDEX
    Explanations

    financial strength

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manu
    -0.09
     Alley
    -0.08
     amazed
    -0.08
     мәт
    -0.08
     subtract
    -0.08
    >↵↵
    -0.08
    екст
    -0.07
     sensit
    -0.07
     kuongeza
    -0.07
    ಮಂತ್ರ
    -0.07
    POSITIVE LOGITS
    信誉
    0.11
     안정
    0.10
     Stability
    0.10
    可靠
    0.10
     stability
    0.09
    稳定
    0.09
     reputable
    0.09
     assures
    0.09
     ಚೆ
    0.08
     надеж
    0.08
    Act Density 0.023%

    No Known Activations