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

    Neuronpedia

    INDEX
    Explanations

    advertisement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ча
    -0.07
     עבור
    -0.07
    开拓
    -0.07
    K
    -0.07
    �
    -0.07
    较
    -0.07
     associated
    -0.07
    支出
    -0.07
    侧重
    -0.06
     "\<
    -0.06
    POSITIVE LOGITS
    ôtel
    0.08
    storms
    0.07
     Freddy
    0.07
     roofs
    0.07
    念头
    0.07
    ettel
    0.07
     Happ
    0.07
     정도
    0.07
    .hand
    0.07
    .caption
    0.07
    Act Density 0.005%

    No Known Activations