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

    Neuronpedia

    INDEX
    Explanations

    words related to confirmation and verification processes

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

    multilingual word fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Olson
    -0.49
     Cohen
    -0.47
    _
    -0.45
     Simons
    -0.45
     
    -0.44
     Tri
    -0.44
     dan
    -0.44
    land
    -0.44
    1
    -0.44
     Booth
    -0.43
    POSITIVE LOGITS
     queſta
    0.77
     defaultstate
    0.76
     Houſe
    0.74
    ſelf
    0.71
     betweenstory
    0.71
    antaranya
    0.70
     Conſ
    0.67
     للاسماء
    0.66
    findpost
    0.65
     AssemblyCompany
    0.65
    Act Density 0.010%

    No Known Activations