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

    Neuronpedia

    INDEX
    Explanations

    sequences of placeholders or underscores

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

    internationalized UI strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.46
    AndroidJUnit
    -0.42
    principalColumn
    -0.40
     handleMessage
    -0.39
    /**
    -0.38
     MaterialApp
    -0.37
    Rptr
    -0.36
    TestingModule
    -0.36
    GIVEREF
    -0.35
    ChildScrollView
    -0.35
    POSITIVE LOGITS
    Diweddarwch
    0.53
     otomatig
    0.51
     paired
    0.49
     karşılaş
    0.49
    vorschaubild
    0.48
     suspendu
    0.48
     flagged
    0.47
    csolódó
    0.46
    𝟸
    0.46
    elry
    0.46
    Act Density 0.004%

    No Known Activations