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

    Neuronpedia

    INDEX
    Explanations

    names and their meanings, particularly in relation to cultural significance

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

    names followed by descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    COLN
    -0.39
     enrich
    -0.36
    zzleHttp
    -0.35
    Билгалдахарш
    -0.35
    ẨM
    -0.34
     gesprek
    -0.33
    ruma
    -0.32
     Campaign
    -0.32
     Foxes
    -0.32
    Ronnie
    -0.32
    POSITIVE LOGITS
    Autoritní
    0.71
    afficheront
    0.60
    tanleria
    0.60
    oa̍t
    0.52
     resourceCulture
    0.52
    magitan
    0.52
     Numerade
    0.52
     kaarangay
    0.51
    alakip
    0.47
     '\\;'
    0.46
    Act Density 0.148%

    No Known Activations