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

    Neuronpedia

    INDEX
    Explanations

    technical terminology and structure commonly used in programming or mathematical contexts

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

    induction hypothesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RectangleBorder
    -0.60
     ब्रेकडाउन
    -0.59
    TagMode
    -0.51
     GenerationType
    -0.48
    enumi
    -0.47
    tvguidetime
    -0.43
    eapon
    -0.43
    chließ
    -0.42
    eqn
    -0.42
    AxisAlignment
    -0.42
    POSITIVE LOGITS
     rhestr
    0.42
     насељу
    0.41
    новништво
    0.40
    RTSN
    0.39
    CreateModel
    0.38
    exitRule
    0.36
    omu
    0.36
    ovina
    0.35
    Outline
    0.35
    ETER
    0.35
    Act Density 0.263%

    No Known Activations