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

    Neuronpedia

    INDEX
    Explanations

    Augustine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    未
    -0.07
     encourages
    -0.07
     未
    -0.07
     uncert
    -0.06
     Вол
    -0.06
    HEMA
    -0.06
    审核
    -0.06
    responsive
    -0.06
     الس
    -0.06
     ней
    -0.06
    POSITIVE LOGITS
    igram
    0.07
    .kr
    0.07
    anth
    0.07
    /ns
    0.06
    ipzig
    0.06
    ····
    0.06
    альні
    0.06
    atform
    0.06
    _dimensions
    0.06
    rax
    0.06
    Act Density 0.008%

    No Known Activations