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

    Neuronpedia

    INDEX
    Explanations

    discussing or summarizing text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    常に
    0.81
     mindig
    0.79
     emiss
    0.79
     creations
    0.77
     vyr
    0.77
     দরজা
    0.77
     مرح
    0.75
     jederzeit
    0.72
     jednotliv
    0.72
    eniem
    0.71
    POSITIVE LOGITS
     discusses
    1.99
     excerpt
    1.91
     discussing
    1.84
     excerpts
    1.78
     quoted
    1.73
     cited
    1.60
     discuss
    1.50
     quotes
    1.50
     discussion
    1.50
     summarizing
    1.48
    Act Density 0.309%

    No Known Activations