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

    Neuronpedia

    INDEX
    Explanations

    example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     корм
    -0.07
    ��
    -0.07
    وجود
    -0.07
    -all
    -0.06
    ότη
    -0.06
    наслідок
    -0.06
    _controller
    -0.06
    ійно
    -0.06
    ii
    -0.06
    ckill
    -0.06
    POSITIVE LOGITS
    $core
    0.07
     seminar
    0.07
     ecology
    0.06
    kus
    0.06
    !
↵
    0.06
     Achie
    0.06
     lebih
    0.06
    Deque
    0.06
    τερη
    0.06
    )

↵
    0.06
    Act Density 0.044%

    No Known Activations