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

    Neuronpedia

    INDEX
    Explanations

    references to study design and methodology

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

    describing study types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    withIdentifier
    -0.48
    windowFixed
    -0.48
     SwitchCompat
    -0.47
    poň
    -0.44
     cæ
    -0.44
     quæ
    -0.43
     показа
    -0.42
     awakeFromNib
    -0.41
     remarqué
    -0.39
    épisode
    -0.39
    POSITIVE LOGITS
    VersionUID
    0.51
     auprès
    0.49
    Ӕ
    0.46
     recruited
    0.45
     esternos
    0.44
     kasarigan
    0.42
     prostřed
    0.41
    Życiorys
    0.41
     dilaksanakan
    0.41
     involve
    0.40
    Act Density 0.120%

    No Known Activations