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

    Neuronpedia

    INDEX
    Explanations

    hesitant curiosity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     psychedelic
    1.66
     showdown
    1.60
     pasta
    1.60
     vocals
    1.58
     multiplayer
    1.57
     python
    1.57
     arithmetic
    1.56
     dexterity
    1.55
     semantic
    1.55
     sedan
    1.55
    POSITIVE LOGITS
    For
    2.98
    The
    2.84
    In
    2.77
    As
    2.76
    But
    2.76
    However
    2.74
    Not
    2.69
    That
    2.67
    To
    2.66
    From
    2.65
    Act Density 0.585%

    No Known Activations