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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "last" and relate it to concepts of time

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

    last year's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.66
     кӀ
    -0.53
    adaptiveStyles
    -0.52
     nakalista
    -0.51
    ISupport
    -0.50
    enterOuterAlt
    -0.50
    ArgsConstructor
    -0.50
     الحره
    -0.49
    LabelTagHelper
    -0.49
    BagLayout
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.44
     Friday
    0.38
     vertra
    0.38
     last
    0.38
    无比
    0.37
     sánh
    0.36
     handshake
    0.35
     verdict
    0.35
     deciso
    0.35
     announced
    0.34
    Act Density 0.016%

    No Known Activations