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

    Neuronpedia

    INDEX
    Explanations

    expressions of opinion and critiques

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

    Text after periods, commas, or "as"

    np_acts-logits-general · gemini-2.0-flash

    contrast and exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.40
     himo
    -0.34
    elemField
    -0.33
    Inf
    -0.32
    ánto
    -0.32
     instig
    -0.32
     отре
    -0.32
    vento
    -0.32
    sn
    -0.31
     ROUND
    -0.31
    POSITIVE LOGITS
     tuttavia
    0.56
     però
    0.55
    ostante
    0.52
     المعيارى
    0.52
    RegressionTest
    0.51
    MemoryWarning
    0.50
     الرياضيه
    0.50
    /**
    0.50
    лтемелер
    0.48
     entanto
    0.48
    Act Density 0.731%

    No Known Activations