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

    Neuronpedia

    INDEX
    Explanations

    lude

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bruno
    -0.07
    IDTH
    -0.07
     guest
    -0.07
    [len
    -0.06
    Being
    -0.06
    .HttpSession
    -0.06
     Swal
    -0.06
     ball
    -0.06
     gestures
    -0.06
    距离
    -0.06
    POSITIVE LOGITS
     Availability
    0.07
    柳州
    0.07
    走廊
    0.07
    ALLED
    0.07
    反对
    0.07
     ack
    0.07
     ח
    0.07
    �
    0.07
    AZ
    0.07
    plement
    0.07
    Act Density 0.000%

    No Known Activations