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

    Neuronpedia

    INDEX
    Explanations

    knowing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tuple
    -0.07
    ột
    -0.06
     elem
    -0.06
    .Resource
    -0.06
    points
    -0.06
     DETAILS
    -0.06
    (tuple
    -0.06
    itial
    -0.06
     prisons
    -0.06
     Braun
    -0.06
    POSITIVE LOGITS
     knowing
    0.11
     Knowing
    0.09
     sat
    0.07
    Knowing
    0.07
    ([]);↵
    0.07
     unaware
    0.07
    aring
    0.07
    _REQ
    0.06
     agreeing
    0.06
     "'",
    0.06
    Act Density 0.010%

    No Known Activations