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

    Neuronpedia

    INDEX
    Explanations

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (holder
    -0.07
     amet
    -0.06
    Incre
    -0.06
    布
    -0.06
    engu
    -0.06
    Dry
    -0.06
    (EC
    -0.06
    шили
    -0.06
    .ALL
    -0.06
    Hint
    -0.06
    POSITIVE LOGITS
     stair
    0.06
    :hover
    0.06
    /)
    0.06
    ""↵
    0.06
    **
    0.06
     nichts
    0.06
    .framework
    0.06
    二二二二
    0.06
    !"
    0.06
    !”
    0.06
    Act Density 0.011%

    No Known Activations