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

    Neuronpedia

    INDEX
    Explanations

    react

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     number
    -0.08
     Number
    -0.08
     numbering
    -0.07
     short
    -0.07
    िसम
    -0.07
    düm
    -0.07
    dump
    -0.07
     intellig
    -0.07
     sü
    -0.07
    _sum
    -0.07
    POSITIVE LOGITS
    act
    0.09
     Martinez
    0.08
    elez
    0.07
    yect
    0.07
    /react
    0.07
     Leon
    0.07
     RX
    0.07
     حين
    0.07
    feedback
    0.07
    acting
    0.07
    Act Density 0.025%

    No Known Activations