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

    Neuronpedia

    INDEX
    Explanations

    lr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iri
    -0.07
    iid
    -0.06
     범
    -0.06
    备
    -0.06
    ethyl
    -0.06
    处理
    -0.06
     purity
    -0.06
     decryption
    -0.06
    eliminar
    -0.06
     RED
    -0.06
    POSITIVE LOGITS
     Katie
    0.06
     začátku
    0.06
     *↵
    0.06
     投稿日
    0.06
     cep
    0.06
     Uint
    0.06
     Vick
    0.06
     徒
    0.06
     Wander
    0.06
    Miami
    0.06
    Act Density 0.018%

    No Known Activations