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

    Neuronpedia

    INDEX
    Explanations

    putting yourself out there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    KD
    -0.07
    ��
    -0.07
     بندی
    -0.07
    幻
    -0.07
    Answers
    -0.07
     eing
    -0.06
     unserialize
    -0.06
    ierung
    -0.06
    ιώ
    -0.06
     Phật
    -0.06
    POSITIVE LOGITS
     citing
    0.06
    -non
    0.06
     yaşayan
    0.06
     lexical
    0.06
     trhu
    0.06
     créer
    0.06
    Kom
    0.06
     promoter
    0.05
     Breitbart
    0.05
     "_
    0.05
    Act Density 0.008%

    No Known Activations