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

    Neuronpedia

    INDEX
    Explanations

    high-frequency occurrences of specific phrases or terms

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

    "parameters", "options", or "field" after "The"/"the"

    np_acts-logits-general · gemini-2.0-flash

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.91
     betweenstory
    -0.76
    uttavia
    -0.72
     estekak
    -0.72
    nocześnie
    -0.65
     Italijanski
    -0.64
    =$?
    -0.62
     ModelRenderer
    -0.61
    latego
    -0.61
    حياتها
    -0.61
    POSITIVE LOGITS
     تضيفلها
    0.70
     Chwiliwch
    0.63
    sterious
    0.57
    seiti
    0.55
    ndre
    0.55
    </em>
    0.54
     بيها
    0.54
    matic
    0.53
    zeitige
    0.52
    tain
    0.51
    Act Density 0.421%

    No Known Activations