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

    Neuronpedia

    INDEX
    Explanations

    temporal phrases indicating time periods or sequences

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

    Numbers followed by "through" or "on"

    np_acts-logits-general · gemini-2.0-flash

    years through or on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intios
    -0.54
    ()]
    -0.51
    หว่าง
    -0.51
    izarea
    -0.51
    onomía
    -0.50
    |<
    -0.49
    ventus
    -0.48
    ASX
    -0.48
    :///
    -0.47
    PickerController
    -0.47
    POSITIVE LOGITS
     onwards
    2.19
     onward
    1.95
     forward
    1.43
     upwards
    1.26
    forward
    1.14
     upward
    1.14
     adelante
    1.09
     downwards
    1.07
     forwards
    1.04
    Forward
    1.00
    Act Density 0.171%

    No Known Activations