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

    Neuronpedia

    INDEX
    Explanations

    Personal opinions and experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    The
    -0.07
     Action
    -0.07
    After
    -0.07
     action
    -0.07
     To
    -0.07
     gruesome
    -0.07
     Fantasy
    -0.07
     bağlantı
    -0.07
     Party
    -0.07
     TO
    -0.06
    POSITIVE LOGITS
     their
    0.08
    ประ
    0.07
     볼
    0.06
     your
    0.06
    �
    0.06
    -orange
    0.06
    сутств
    0.06
    。我
    0.06
     tua
    0.06
     his
    0.06
    Act Density 0.080%

    No Known Activations