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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to measurements and performance metrics

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

    section image

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſol
    -0.49
     ſal
    -0.48
     pleaſure
    -0.47
     Inſ
    -0.45
     ſch
    -0.42
     Monfieur
    -0.39
     Reſ
    -0.37
    gangssprach
    -0.37
     Eſ
    -0.36
     Perſ
    -0.35
    POSITIVE LOGITS
    expandindo
    0.91
    GraphicsUnit
    0.66
     resourceCulture
    0.63
    ValueStyle
    0.62
     Италијани
    0.61
     '\\;'
    0.61
    GEBURTSDATUM
    0.59
    Derbyniad
    0.57
     transfieras
    0.57
    RTCK
    0.57
    Act Density 0.133%

    No Known Activations