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

    Neuronpedia

    INDEX
    Explanations

    corporate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animals
    -0.09
     Administrator
    -0.09
    animals
    -0.08
    Administrator
    -0.08
     nevez
    -0.08
     vermitteln
    -0.08
     përd
    -0.07
    管理员
    -0.07
     teasing
    -0.07
     rehears
    -0.07
    POSITIVE LOGITS
    旗下
    0.10
    Transform
    0.09
     procurement
    0.09
     transformação
    0.08
     transformación
    0.08
     trasform
    0.08
     Transform
    0.08
     struggled
    0.08
     deciso
    0.08
    Commit
    0.07
    Act Density 0.046%

    No Known Activations