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

    Neuronpedia

    INDEX
    Explanations

    Academy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озмож
    -0.07
    /lang
    -0.07
     повед
    -0.06
     παιδ
    -0.06
    Fans
    -0.06
    ddd
    -0.06
    出版社
    -0.06
     adec
    -0.06
     Нав
    -0.06
    /css
    -0.06
    POSITIVE LOGITS
     differential
    0.06
     fundraising
    0.06
     Differential
    0.06
     �
    0.06
    .ev
    0.06
    τύ
    0.06
    _radio
    0.06
    Truthy
    0.06
     slid
    0.06
    ΤΡ
    0.06
    Act Density 0.027%

    No Known Activations