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

    Neuronpedia

    INDEX
    Explanations

    transactional and procedural language related to systems and processes

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

    then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thumb
    -0.43
    ABUL
    -0.42
    стьян
    -0.40
    butan
    -0.39
     catal
    -0.38
    millan
    -0.36
    yer
    -0.36
     nar
    -0.36
    בן
    -0.36
     ben
    -0.36
    POSITIVE LOGITS
     beginnetje
    0.57
    然後
    0.55
    errHandler
    0.55
    Затем
    0.54
    InitVars
    0.53
     then
    0.52
    ագրություններ
    0.51
     apoi
    0.51
     navideños
    0.50
    然后
    0.49
    Act Density 0.080%

    No Known Activations