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

    Neuronpedia

    INDEX
    Explanations

    phrases related to data management and processing

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

    or characters preceding mathematical/scientific notation

    np_acts-logits-general · gemini-2.0-flash

    is estimated, are therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fromnode
    -0.55
    ">—
    -0.52
     Little
    -0.50
    ítu
    -0.49
     referrerpolicy
    -0.48
     LITTLE
    -0.46
    Little
    -0.46
     COMPOS
    -0.46
     Temptation
    -0.45
     Robertson
    -0.45
    POSITIVE LOGITS
     définiti
    0.59
     chimiques
    0.57
     AssemblyCulture
    0.57
    MLLoader
    0.55
     enkelte
    0.55
     sää
    0.54
     alimentaires
    0.51
    OGND
    0.50
     fallu
    0.49
    ⓧ
    0.48
    Act Density 0.011%

    No Known Activations