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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @RequestMapping
    -0.07
     ml
    -0.07
     redhead
    -0.07
    一只
    -0.07
     полу
    -0.07
    QL
    -0.06
     Venue
    -0.06
    _successful
    -0.06
    !I
    -0.06
    RequestMapping
    -0.06
    POSITIVE LOGITS
    _numbers
    0.07
    不同的
    0.07
    dıklarını
    0.07
    det
    0.06
    �
    0.06
    ovan
    0.06
    긑
    0.06
    徕
    0.06
    对待
    0.06
    [self
    0.06
    Act Density 0.156%

    No Known Activations