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

    Neuronpedia

    INDEX
    Explanations

    quantities or mentions of "extra."

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

    "extra"

    np_acts-logits-general · gemini-2.0-flash

    extra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    couvrez
    -0.56
     cartera
    -0.51
     Respuesta
    -0.51
     představ
    -0.49
     Lingkungan
    -0.48
     للمعارف
    -0.47
     gezicht
    -0.46
     carteira
    -0.45
     matahari
    -0.44
     Masyarakat
    -0.44
    POSITIVE LOGITS
     extra
    1.34
     EXTRA
    1.32
     Extra
    1.30
    Extra
    1.22
    extra
    1.21
    EXTRA
    1.15
    xtra
    1.02
     extras
    1.01
     ekstra
    0.97
     Extras
    0.96
    Act Density 0.099%

    No Known Activations