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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trypt
    0.32
     trophic
    0.32
     xanth
    0.31
     cannabinoids
    0.31
     hydroxyl
    0.31
     sorption
    0.30
     amines
    0.30
     leukocytes
    0.30
     calcareous
    0.30
    ،
    0.30
    POSITIVE LOGITS
    if
    0.44
    //
    0.35
    import
    0.35
    let
    0.33
    for
    0.32
    while
    0.32
    this
    0.32
    #
    0.31
    using
    0.31
    var
    0.30
    Act Density 2.029%

    No Known Activations