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

    Neuronpedia

    INDEX
    Explanations

    references to a variety of subjects, particularly recurring elements in complex concepts or discussions

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

    following "the"

    np_acts-logits-general · gemini-2.0-flash

    consequent nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    -0.82
     entweder
    -0.74
     either
    -0.69
    either
    -0.65
     nemlig
    -0.65
     firstly
    -0.61
     einerseits
    -0.60
    ():
    -0.58
    Either
    -0.57
     těchto
    -0.57
    POSITIVE LOGITS
     consiguiente
    1.26
     consequent
    1.26
     importantly
    1.13
    何より
    1.12
     daraus
    1.05
     subsequent
    1.02
     évent
    0.97
     daarbij
    0.93
     whatnot
    0.90
     resultant
    0.89
    Act Density 0.450%

    No Known Activations