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

    Neuronpedia

    INDEX
    Explanations

    complex mathematical expressions or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Superscripted tokens followed by "abc"

    np_acts-logits-general · gemini-2.0-flash

    abc and similar strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     createState
    -0.58
     Quentin
    -0.56
    īts
    -0.56
    mær
    -0.52
    Hentet
    -0.52
     بيها
    -0.50
    gın
    -0.49
    torque
    -0.49
     muualla
    -0.49
    Pocket
    -0.48
    POSITIVE LOGITS
     AB
    1.10
    AB
    1.04
     ABC
    0.93
     ab
    0.92
     abc
    0.91
    ABC
    0.90
    abc
    0.89
    ab
    0.86
    xy
    0.86
    XY
    0.82
    Act Density 1.621%

    No Known Activations