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

    Neuronpedia

    INDEX
    Explanations

    Judges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    追加
    -0.07
    CASCADE
    -0.06
     tin
    -0.06
    본
    -0.06
     gerekmektedir
    -0.06
    .ByteArray
    -0.06
     Magnet
    -0.06
    ().↵
    -0.06
     Unicorn
    -0.06
     nấu
    -0.06
    POSITIVE LOGITS
    İŞ
    0.07
    metro
    0.06
     zih
    0.06
    (confirm
    0.06
    .point
    0.06
    _plots
    0.06
    (Register
    0.06
     compounded
    0.06
    acing
    0.06
     oppressed
    0.05
    Act Density 0.003%

    No Known Activations