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

    Neuronpedia

    INDEX
    Explanations

    sequences of continuous whitespace characters

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

    CPL, Install, class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.54
     betweenstory
    -0.52
     estekak
    -0.52
    principalColumn
    -0.50
    setVerticalGroup
    -0.48
    RegressionTest
    -0.46
    UnknownFieldSet
    -0.45
     tänka
    -0.44
    SharedCtor
    -0.43
    UpInside
    -0.42
    POSITIVE LOGITS
     conflict
    0.45
    ⟬
    0.45
    CCER
    0.45
     RelativeLayout
    0.44
    itename
    0.43
     Keats
    0.42
     Shakspeare
    0.41
     effectively
    0.41
     שוליים
    0.40
     Jove
    0.40
    Act Density 0.001%

    No Known Activations