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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority and command

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

    equal to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Allo
    -0.38
    KommentareTeilen
    -0.36
    fla
    -0.34
    thin
    -0.33
    }))
    -0.31
    cart
    -0.31
    yea
    -0.31
    ीय
    -0.30
     Tor
    -0.30
    ⇑
    -0.30
    POSITIVE LOGITS
    于
    0.93
    於
    0.74
    于是
    0.67
     disambiguazione
    0.63
    於是
    0.63
    ftagPool
    0.61
    Tikang
    0.60
    帖最后由
    0.59
    ReusableCell
    0.57
    tagHelperRunner
    0.54
    Act Density 0.070%

    No Known Activations