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

    Neuronpedia

    INDEX
    Explanations

    sequences of numerical values and their occurrences

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

    alphanumeric sequences and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.57
    Atsauces
    -0.55
    ToBounds
    -0.54
    isContained
    -0.54
     miniaturka
    -0.54
     الحره
    -0.53
     dezelve
    -0.53
    Ārējās
    -0.53
    archiwizowane
    -0.53
    -0.52
    POSITIVE LOGITS
     ABC
    0.56
     abc
    0.55
     XYZ
    0.55
    ABC
    0.52
    NOPQRST
    0.51
    abcdefghijklmnop
    0.50
    qrstuvwxyz
    0.50
    abc
    0.49
    abcdef
    0.48
    abcd
    0.47
    Act Density 0.149%

    No Known Activations