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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical or scientific concepts of inversion

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

    inversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    testens
    -0.52
    كويكب
    -0.52
    googleapis
    -0.50
    Alike
    -0.50
    Daemon
    -0.50
    CharCode
    -0.48
     Exacts
    -0.47
     Waray
    -0.47
     őket
    -0.47
    millis
    -0.47
    POSITIVE LOGITS
     inversion
    1.96
     inver
    1.82
     invert
    1.70
     Inversion
    1.66
    inversion
    1.66
     inverted
    1.45
     Inver
    1.41
    inver
    1.39
    invert
    1.38
    Inver
    1.38
    Act Density 0.005%

    No Known Activations