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

    Neuronpedia

    INDEX
    Explanations

    names and identifiers related to authors or contributors in a document

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

    Comes after names or aliases

    np_acts-logits-general · gemini-2.0-flash

    citations with names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    存于互联网档案馆
    -0.55
    forhold
    -0.50
    glog
    -0.49
     Busan
    -0.48
     surla
    -0.48
    nival
    -0.47
     abbraccio
    -0.47
    /*:
    -0.47
    //:
    -0.45
     Hermans
    -0.45
    POSITIVE LOGITS
     AttributeSet
    0.73
     Tet
    0.70
     Hide
    0.65
     Mas
    0.65
     Masa
    0.63
     Roskov
    0.63
    الحياه
    0.63
     Kaz
    0.62
    EndContext
    0.62
    +#+
    0.59
    Act Density 0.197%

    No Known Activations