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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     periodic
    -0.07
     stimulate
    -0.07
     Responsibility
    -0.07
    -X
    -0.07
     redirect
    -0.07
    -state
    -0.06
    �
    -0.06
     bias
    -0.06
    (Person
    -0.06
     необходимости
    -0.06
    POSITIVE LOGITS
     Cypress
    0.06
     nem
    0.06
     whims
    0.06
     ol
    0.06
     sky
    0.06
     hissed
    0.06
    .backgroundColor
    0.06
    .↵↵↵↵
    0.06
     вит
    0.06
     [<
    0.05
    Act Density 0.016%

    No Known Activations