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

    Neuronpedia

    INDEX
    Explanations

    "," and "and"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrog
    -0.06
    -designed
    -0.06
    notice
    -0.06
    ськими
    -0.06
    目前
    -0.06
     서버
    -0.06
    ชาย
    -0.06
     patriot
    -0.06
     ।↵↵
    -0.06
    μένων
    -0.06
    POSITIVE LOGITS
     Abb
    0.07
    249
    0.07
     arb
    0.07
     altercation
    0.07
     SEL
    0.06
     calf
    0.06
     ор
    0.06
     scrollbar
    0.06
    atatype
    0.06
    'r
    0.06
    Act Density 0.039%

    No Known Activations