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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Test
    -0.07
     coding
    -0.07
     repression
    -0.07
     Tail
    -0.07
     seed
    -0.07
    label
    -0.06
     Test
    -0.06
     sacrific
    -0.06
     Slide
    -0.06
     Education
    -0.06
    POSITIVE LOGITS
    any
    0.08
    /net
    0.07
    -An
    0.07
    atypes
    0.07
    >An
    0.07
    ы
    0.06
    áp
    0.06
    -touch
    0.06
    anlar
    0.06
    (math
    0.06
    Act Density 0.009%

    No Known Activations