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

    Neuronpedia

    INDEX
    Explanations

    quantitative measurements related to scores and performance metrics

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

    float numbers with decimal points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    örs
    -0.39
     insuffisamment
    -0.38
    keres
    -0.37
    Externé
    -0.37
    civil
    -0.37
    picasso
    -0.36
    eche
    -0.36
     encu
    -0.36
    Билгалдахарш
    -0.35
    ish
    -0.35
    POSITIVE LOGITS
    دانشنامهٔ
    0.54
    SequentialGroup
    0.52
    Cyfarwyddwr
    0.50
    ConstraintMaker
    0.50
    twimg
    0.50
    verwijspagina
    0.49
    ikusbot
    0.49
     transfieras
    0.48
    ValueGeneration
    0.48
    ChildScrollView
    0.48
    Act Density 0.056%

    No Known Activations