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

    Neuronpedia

    INDEX
    Explanations

    classify

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     concentrates
    -0.07
     submission
    -0.07
     COVID
    -0.07
     illustration
    -0.06
    .nan
    -0.06
     Hil
    -0.06
    '";↵
    -0.06
     thr
    -0.06
     offspring
    -0.06
     outraged
    -0.06
    POSITIVE LOGITS
    仅
    0.08
    regon
    0.07
     قد
    0.07
     adlı
    0.06
     '<%=
    0.06
    ><?=
    0.06
     حتی
    0.06
    ็ตาม
    0.06
     billeder
    0.06
     )↵↵↵↵↵↵↵↵
    0.06
    Act Density 0.014%

    No Known Activations