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

    Neuronpedia

    INDEX
    Explanations

    references to prior studies and research

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

    preceding academic or legal terms

    np_acts-logits-general · gemini-2.0-flash

    previous or prior information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     później
    -0.64
     senere
    -0.63
     later
    -0.62
     afterward
    -0.59
     awalnya
    -0.59
     hereafter
    -0.58
     später
    -0.58
     pozdě
    -0.57
     européennes
    -0.55
     kés
    -0.54
    POSITIVE LOGITS
     generations
    1.11
    itisation
    1.06
     iterations
    0.87
     incar
    0.84
     years
    0.83
     generation
    0.80
     versions
    0.78
     unsuccessful
    0.77
    mentioned
    0.77
     incarnation
    0.76
    Act Density 0.137%

    No Known Activations