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

    Neuronpedia

    INDEX
    Explanations

    .</

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    curity
    -0.08
    Watcher
    -0.07
    -parameter
    -0.07
     ErrorCode
    -0.07
     colonies
    -0.07
     ủy
    -0.07
    -count
    -0.07
    -elements
    -0.07
    marginLeft
    -0.07
    gv
    -0.07
    POSITIVE LOGITS
    TestId
    0.07
     उसन
    0.06
     deem
    0.06
     parten
    0.06
    broker
    0.06
     빠
    0.06
    'It
    0.05
    咲
    0.05
     wan
    0.05
     neměl
    0.05
    Act Density 0.011%

    No Known Activations