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

    Neuronpedia

    INDEX
    Explanations

    pharmaceuticals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Whip
    -0.07
    电信
    -0.07
     Arts
    -0.07
     transmitting
    -0.07
    Interpreter
    -0.06
     since
    -0.06
     prudent
    -0.06
    態度
    -0.06
     odp
    -0.06
    俭
    -0.06
    POSITIVE LOGITS
    ↯
    0.08
    🔬
    0.07
    VERBOSE
    0.07
     momentos
    0.07
    .;
    0.07
    "=>
    0.07
    没有什么
    0.07
    领域
    0.07
    �
    0.07
    Ō
    0.07
    Act Density 0.112%

    No Known Activations