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

    Neuronpedia

    INDEX
    Explanations

    explanations or descriptions of processes and methodologies

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

    how it works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.53
    
    -0.49
    antaranya
    -0.45
     purpoſe
    -0.43
     pleaſure
    -0.43
    reportWebVitals
    -0.42
    hoeddwyd
    -0.42
    }');
    -0.42
    AddTagHelper
    -0.42
     ſtate
    -0.42
    POSITIVE LOGITS
     EconPapers
    0.46
    Hentet
    0.44
     damit
    0.43
    awaiter
    0.40
    ccional
    0.39
    تقاوى
    0.39
     indirectly
    0.38
     thus
    0.38
    complexType
    0.37
     twice
    0.37
    Act Density 0.246%

    No Known Activations