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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     이거
    0.56
     unsurprisingly
    0.55
     devoid
    0.55
     encompasses
    0.52
     Remarkably
    0.51
     denoting
    0.51
     denotes
    0.51
    Surprisingly
    0.51
     resembling
    0.51
     Calculates
    0.50
    POSITIVE LOGITS
     possibility
    1.04
     latter
    0.91
    mselves
    0.90
     entirety
    0.86
     presence
    0.85
     same
    0.82
     amount
    0.81
     difference
    0.81
     latest
    0.79
     aforementioned
    0.79
    Act Density 0.348%

    No Known Activations