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

    Neuronpedia

    INDEX
    Explanations

    icons and representations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aprove
    -0.07
    .constants
    -0.06
     giants
    -0.06
     wings
    -0.06
    ue
    -0.06
    해
    -0.06
    bruar
    -0.06
    목
    -0.06
    istring
    -0.06
    UE
    -0.05
    POSITIVE LOGITS
    0.07
    Slice
    0.07
     그녀의
    0.07
    ยาน
    0.07
     nád
    0.06
    وزيع
    0.06
    0.06
    FormItem
    0.06
     princip
    0.06
    stanov
    0.06
    Act Density 0.074%

    No Known Activations