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

    Neuronpedia

    INDEX
    Explanations

    of followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ed
    0.51
    book
    0.38
    alike
    0.38
    over
    0.37
    at
    0.36
    the
    0.36
    Only
    0.36
    in
    0.35
    out
    0.35
    stituto
    0.35
    POSITIVE LOGITS
     doom
    0.43
     разрабо
    0.42
    詆
    0.41
     course
    0.40
    ESSION
    0.39
    рда
    0.39
     Doom
    0.39
    ومه
    0.39
     Thrones
    0.38
     イ
    0.38
    Act Density 0.037%

    No Known Activations