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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new"

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

    declaration of new types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     propOrder
    -0.66
    "}")
    -0.48
     <=",
    -0.46
     <>",
    -0.46
    Jereo
    -0.44
     Numerade
    -0.43
     Jungen
    -0.43
    principalColumn
    -0.42
     veau
    -0.42
    cessite
    -0.41
    POSITIVE LOGITS
    RTDA
    0.48
    EDEFAULT
    0.46
     AspNetCore
    0.46
    matchCondition
    0.42
     otomatig
    0.41
    DebuggerStep
    0.41
    OCCURRED
    0.41
    toMatchSnapshot
    0.39
     gekomen
    0.38
    colhead
    0.38
    Act Density 0.003%

    No Known Activations