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

    Neuronpedia

    INDEX
    Explanations

    terms related to reliability and standardization in research

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

    observer agreement and reproducibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uxxxx
    -0.63
     للمعارف
    -0.62
    SequentialGroup
    -0.62
     CreateTagHelper
    -0.58
    dflare
    -0.53
    AndEndTag
    -0.53
    IUrlHelper
    -0.50
     HasFactory
    -0.49
     Roskov
    -0.48
     <<<<<<<<<<<<<<
    -0.46
    POSITIVE LOGITS
     okaz
    0.38
     acord
    0.34
    なく
    0.34
     ihti
    0.33
     einmal
    0.33
     Sang
    0.32
    Rem
    0.32
    künfte
    0.32
    Sang
    0.31
     sand
    0.31
    Act Density 0.152%

    No Known Activations