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

    Neuronpedia

    INDEX
    Explanations

    instances and references to personal introspection or reflection

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

    looking around places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.60
    setVerticalGroup
    -0.57
     istore
    -0.53
     autorytatywna
    -0.53
     وتسجيلات
    -0.52
     BoxFit
    -0.51
    ReusableCell
    -0.51
    RectangleBorder
    -0.49
     Bak
    -0.48
    Bak
    -0.48
    POSITIVE LOGITS
     utafitiHapana
    0.35
    ponses
    0.34
     selamat
    0.34
    Tē
    0.34
     repente
    0.33
    unknownFields
    0.33
     ciudadana
    0.32
     Lebens
    0.32
    SerializeField
    0.32
     sustancia
    0.31
    Act Density 0.091%

    No Known Activations