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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences and contacts, particularly phone numbers

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

    Numbers followed by specific sizes

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isamment
    -0.48
     Italij
    -0.47
     preſent
    -0.47
     Angaben
    -0.47
     productivo
    -0.47
    tanleria
    -0.46
     فريبيس
    -0.44
     števil
    -0.44
     splet
    -0.43
    ziasztok
    -0.43
    POSITIVE LOGITS
     Dec
    0.42
     Dialogue
    0.41
     Shared
    0.40
    oznam
    0.40
     RM
    0.39
    numerusform
    0.39
     rotor
    0.38
     Regional
    0.38
     Sept
    0.38
     MainAxisSize
    0.38
    Act Density 0.208%

    No Known Activations