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

    Neuronpedia

    INDEX
    Explanations

    package main declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    1.91
    for
    1.73
    from
    1.72
    entire
    1.71
    using
    1.71
    int
    1.70
    boolean
    1.66
    have
    1.66
    with
    1.63
    based
    1.63
    POSITIVE LOGITS
     my
    1.94
     mijn
    1.81
     m
    1.75
     z
    1.75
     k
    1.74
     tres
    1.74
     nama
    1.73
     meine
    1.73
     p
    1.72
     r
    1.72
    Act Density 1.190%

    No Known Activations