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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and formulas involving variables and constants

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

    fractions and mathematical formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.66
    DebuggerNonUser
    -0.57
     Chwiliwch
    -0.55
     OnInit
    -0.54
    msgTypes
    -0.54
    Legături
    -0.54
    MethodManager
    -0.54
    出版年
    -0.53
    EnableWeb
    -0.50
     Paglinawan
    -0.48
    POSITIVE LOGITS
    につ
    0.38
     bodys
    0.33
     hack
    0.31
     elephants
    0.31
    럴
    0.31
     orphan
    0.31
     glob
    0.31
     Evid
    0.30
     currents
    0.30
    endy
    0.30
    Act Density 0.118%

    No Known Activations