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

    Neuronpedia

    INDEX
    Explanations

    method calls or functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     occupy
    0.42
     thinly
    0.41
     കത്തി
    0.38
     liable
    0.38
     phenomenal
    0.38
     Moody
    0.37
    carbonate
    0.37
    //*
    0.37
     Strauss
    0.37
     Combien
    0.37
    POSITIVE LOGITS
    $_
    0.48
    ::
    0.45
     ::
    0.43
    ::$
    0.42
    ::_
    0.41
    राजनी
    0.40
     Instance
    0.39
    routes
    0.39
    Polit
    0.38
    Routes
    0.38
    Act Density 0.001%

    No Known Activations