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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    בים
    -0.07
     chuyến
    -0.07
    /arch
    -0.07
    どのような
    -0.07
     mooie
    -0.06
     sketches
    -0.06
    жить
    -0.06
    بيل
    -0.06
     Wind
    -0.06
    wrap
    -0.06
    POSITIVE LOGITS
    下面是
    0.07
    :req
    0.07
    痛点
    0.07
    谇
    0.07
    (id
    0.06
     fallback
    0.06
    (pk
    0.06
    _local
    0.06
    Ctr
    0.06
    Fetching
    0.06
    Act Density 0.000%

    No Known Activations