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

    Neuronpedia

    INDEX
    Explanations

    choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Серг
    -0.07
    496
    -0.06
    PIC
    -0.06
     Opr
    -0.06
     tamaño
    -0.06
    .ol
    -0.06
    天天
    -0.06
     Degree
    -0.06
    eventType
    -0.06
    85
    -0.06
    POSITIVE LOGITS
    *m
    0.08
    Ipv
    0.07
     thee
    0.07
    *[
    0.07
     블
    0.07
    =m
    0.06
     �
    0.06
    ').
    0.06
    *>(
    0.06
     mesmo
    0.06
    Act Density 0.031%

    No Known Activations