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

    Neuronpedia

    INDEX
    Explanations

    answer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .requireNonNull
    -0.07
    ᨦ
    -0.07
     passive
    -0.06
    ㎢
    -0.06
    Quiz
    -0.06
    Rather
    -0.06
    .extension
    -0.06
     lekker
    -0.06
    Expiration
    -0.06
     vulnerable
    -0.06
    POSITIVE LOGITS
    呤
    0.07
    ows
    0.07
    陵
    0.07
    isers
    0.07
    疆
    0.06
     Wars
    0.06
    got
    0.06
    劇
    0.06
     Goes
    0.06
    ��
    0.06
    Act Density 0.029%

    No Known Activations