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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses or confirmations

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

    Affirmative words or phrases

    np_acts-logits-general · gemini-2.0-flash

    affirmative response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BrowserModule
    -0.59
    <bos>
    -0.55
    yntaxException
    -0.54
     }?>
    -0.53
    }`}
    -0.53
     gynhyrchwyd
    -0.53
     initComponents
    -0.51
    Presentación
    -0.51
     continúas
    -0.51
    '}}
    -0.50
    POSITIVE LOGITS
     yes
    1.09
     Yep
    0.95
    yes
    0.94
     Yes
    0.90
    Yes
    0.87
     yep
    0.84
     Yup
    0.83
    Yep
    0.83
     yeah
    0.78
    Yup
    0.77
    Act Density 0.153%

    No Known Activations