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

    Neuronpedia

    INDEX
    Explanations

    Personal stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Enc
    -0.07
    ests
    -0.07
    printf
    -0.06
    ości
    -0.06
    bbb
    -0.06
    (sequence
    -0.06
    (ex
    -0.06
    ault
    -0.06
     adult
    -0.06
    เท
    -0.06
    POSITIVE LOGITS
     путем
    0.06
     вигляді
    0.06
     gridView
    0.06
     Cena
    0.06
     headquarters
    0.06
     stehen
    0.06
     supremacist
    0.06
    .gridView
    0.06
    DESCRIPTION
    0.06
    Điều
    0.06
    Act Density 0.066%

    No Known Activations