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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to efficiency and performance metrics

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

    achieved optimal performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UIControlState
    -0.40
     houſe
    -0.38
    
    -0.38
     zy
    -0.37
     cas
    -0.37
    фан
    -0.36
     patro
    -0.36
     otomatig
    -0.36
     cal
    -0.35
    CppCodeGen
    -0.35
    POSITIVE LOGITS
     ModelExpression
    0.60
     logrado
    0.51
     achieved
    0.49
     erzielt
    0.48
     prestasi
    0.48
     achievable
    0.48
     logros
    0.47
     optimized
    0.46
     helft
    0.46
     logra
    0.45
    Act Density 0.121%

    No Known Activations