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

    Neuronpedia

    INDEX
    Explanations

    Internal beliefs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ratio
    -0.09
     jumbo
    -0.08
     ratio
    -0.08
     Rat
    -0.08
     Verhältnis
    -0.08
     Umgebung
    -0.08
     Range
    -0.07
     refer
    -0.07
    aju
    -0.07
     refers
    -0.07
    POSITIVE LOGITS
     profundamente
    0.12
     profondément
    0.11
     deeply
    0.11
    願
    0.10
     profonde
    0.10
     profond
    0.10
     হৃদ
    0.10
     overtu
    0.10
     profundas
    0.09
    真的
    0.09
    Act Density 0.031%

    No Known Activations