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

    Neuronpedia

    INDEX
    Explanations

    operating systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uzman
    -0.07
    محمد
    -0.07
     Matth
    -0.07
    omu
    -0.06
    $o
    -0.06
    afia
    -0.06
     сог
    -0.06
    chat
    -0.06
    oller
    -0.06
    .mem
    -0.06
    POSITIVE LOGITS
    そして
    0.08
    &↵
    0.07
    regnum
    0.06
    $$
    0.06
     SIX
    0.06
    ản
    0.06
    %'↵
    0.06
    алы
    0.06
     *
↵
    0.06
     >&
    0.06
    Act Density 0.022%

    No Known Activations