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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty and uncertainty

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

    that mean "however," "instead," or "really"

    np_acts-logits-general · gemini-2.0-flash

    foreign language adverbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     américa
    -0.50
    tanleria
    -0.45
     habl
    -0.44
     despedida
    -0.43
    seiti
    -0.43
     prés
    -0.43
     asegu
    -0.43
    󠁴
    -0.42
     inconnu
    -0.42
     sarili
    -0.42
    POSITIVE LOGITS
     bard
    0.47
    invokeLater
    0.44
    ább
    0.43
    fram
    0.42
    WriteTagHelper
    0.42
     Probe
    0.41
    Autoritní
    0.41
     defStyleAttr
    0.41
     Nugent
    0.40
    RTSN
    0.40
    Act Density 0.153%

    No Known Activations