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

    Neuronpedia

    INDEX
    Explanations

    is the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ноч
    -0.06
    -license
    -0.06
    vertices
    -0.06
     答
    -0.06
     clicking
    -0.06
     (_.
    -0.06
     ted
    -0.06
     uttered
    -0.06
    -liter
    -0.06
    moment
    -0.06
    POSITIVE LOGITS
     dép
    0.07
    ческая
    0.07
    elsen
    0.06
    کات
    0.06
    _WAIT
    0.06
     lá
    0.06
     insn
    0.06
    $tpl
    0.06
     con
    0.06
    elder
    0.06
    Act Density 0.022%

    No Known Activations