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

    Neuronpedia

    INDEX
    Explanations

    Go (Golang)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.77
     ça
    1.55
     chicken
    1.51
     password
    1.50
     (_,
    1.49
     pointed
    1.48
     habitat
    1.47
     it
    1.45
     stylish
    1.45
     moral
    1.44
    POSITIVE LOGITS
    !!)
    2.58
    ?).
    2.54
    ?),
    2.53
    with
    2.39
    /)
    2.33
    which
    2.26
    including
    2.24
    **)
    2.22
    ..)
    2.19
    from
    2.16
    Act Density 1.030%

    No Known Activations