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

    Neuronpedia

    INDEX
    Explanations

    references to statistics or quantities in a statistical or factual context

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

    According to label and buckle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.88
     lenker
    -0.73
     nahilalakip
    -0.57
     nakalista
    -0.55
     surla
    -0.55
    GTCX
    -0.54
    /**
    -0.53
    manjaro
    -0.49
     ब्रेकडाउन
    -0.49
    ########.
    -0.48
    POSITIVE LOGITS
    olera
    0.39
     force
    0.35
    heit
    0.34
    nię
    0.34
    NATIVE
    0.33
    BagConstraints
    0.32
    belo
    0.31
    ARIO
    0.31
    ARIOS
    0.31
    žel
    0.31
    Act Density 0.028%

    No Known Activations