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

    Neuronpedia

    INDEX
    Explanations

    preventing script crashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    дного
    0.51
     ElevatedButton
    0.50
     डन
    0.50
     UpdateWindow
    0.50
     terminated
    0.49
    terminated
    0.49
     Timurtaş
    0.48
    0.48
     LMP
    0.48
     Fq
    0.48
    POSITIVE LOGITS
    Collect
    0.56
    CYCL
    0.49
    Access
    0.49
     t
    0.48
    Pack
    0.47
    Obs
    0.46
    Cole
    0.46
    CA
    0.45
    Cin
    0.45
    Source
    0.45
    Act Density 0.001%

    No Known Activations