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

    Neuronpedia

    INDEX
    Explanations

    statistical values and performance metrics

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

    Numbers following "and"

    np_acts-logits-general · gemini-2.0-flash

    computational expressions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    apimachinery
    -0.68
    ftances
    -0.64
    يكب
    -0.63
     विश्वसनीयता
    -0.62
    ^(@)
    -0.62
     Efq
    -0.61
    outchouc
    -0.61
     poffible
    -0.61
     <>",
    -0.61
    adeloupe
    -0.60
    POSITIVE LOGITS
     @"/
    0.68
    #
    0.63
    GEBURTSDATUM
    0.56
    AsUp
    0.53
    Демографія
    0.52
    ⚠
    0.51
    rrggbb
    0.49
    Enllaces
    0.49
    +#+
    0.48
     makl
    0.48
    Act Density 0.380%

    No Known Activations