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

    Neuronpedia

    INDEX
    Explanations

    combinatorics and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boas
    -0.07
     pequenas
    -0.07
     મેચ
    -0.07
     મળે
    -0.07
     möglichst
    -0.07
     желательно
    -0.07
    (T
    -0.07
     matched
    -0.07
    ناس
    -0.07
     práticas
    -0.07
    POSITIVE LOGITS
    ADE
    0.09
     ignor
    0.08
     hardcore
    0.08
     censorship
    0.08
    只
    0.08
     käytt
    0.08
     restrict
    0.08
     exclusion
    0.08
     censor
    0.08
     spezial
    0.07
    Act Density 0.015%

    No Known Activations