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

    Neuronpedia

    INDEX
    Explanations

    web domain names and URLs

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

    URLs pointing to specific files or directories

    np_acts-logits-general · gemini-2.0-flash

    domain names followed by /

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     come
    -0.54
     Come
    -0.49
    Come
    -0.48
    COME
    -0.47
    come
    -0.46
     Vordergrund
    -0.45
    тье
    -0.45
     much
    -0.44
    *)((
    -0.44
     a
    -0.42
    POSITIVE LOGITS
     مشين
    0.98
     سكانية
    0.91
    Datuak
    0.89
    Personensuche
    0.82
     nonUne
    0.82
    /~
    0.80
    KommentareTeilen
    0.79
    tagHelperRunner
    0.72
    ็จ
    0.72
    mobileqq
    0.71
    Act Density 0.083%

    No Known Activations