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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal accomplishment and scholarly work

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

    Beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    action verbs and resulting nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brilliant
    -0.87
    Brilliant
    -0.86
    brilliant
    -0.85
     Brilliant
    -0.82
     Signalez
    -0.80
     marvellous
    -0.80
     marvelous
    -0.78
     genius
    -0.77
     superb
    -0.75
     magnificent
    -0.75
    POSITIVE LOGITS
     hopefully
    0.95
    hopefully
    0.90
     Hopefully
    0.84
    Hopefully
    0.77
     myself
    0.73
     my
    0.68
     hope
    0.67
    myself
    0.60
     try
    0.55
     trying
    0.55
    Act Density 0.314%

    No Known Activations