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

    Neuronpedia

    INDEX
    Explanations

    punctuation/conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    厨房
    -0.09
     campaigning
    -0.09
    Disclaimer
    -0.09
    exper
    -0.08
    ority
    -0.08
    face
    -0.08
    装
    -0.08
    大师
    -0.08
    -score
    -0.08
     Peso
    -0.08
    POSITIVE LOGITS
     intermediate
    0.09
     Eventually
    0.08
     включая
    0.08
     eventually
    0.08
     blod
    0.08
     mucus
    0.08
     Intermediate
    0.08
     конеч
    0.08
    Intermediate
    0.08
     termasuk
    0.08
    Act Density 0.013%

    No Known Activations