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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _picker
    -0.07
    (DE
    -0.07
     Remember
    -0.07
     remarkably
    -0.06
    .”↵
    -0.06
    μενη
    -0.06
    ��
    -0.06
     Hob
    -0.06
    233
    -0.06
    chedules
    -0.06
    POSITIVE LOGITS
     animation
    0.07
     itibaren
    0.07
     visuals
    0.06
    的小
    0.06
     comic
    0.06
     vý
    0.06
    [:,
    0.06
     okul
    0.06
     إذا
    0.06
    .assign
    0.06
    Act Density 0.002%

    No Known Activations