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

    Neuronpedia

    INDEX
    Explanations

    specific code terms and syntax

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

    pre-execute on, ATP affinities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.61
     AssemblyVersion
    -0.47
    JAKARTA
    -0.46
     SwitchCompat
    -0.45
    UseVisualStyle
    -0.44
     Jefus
    -0.44
    ppia
    -0.44
    getStringExtra
    -0.42
     ressource
    -0.41
     Савезне
    -0.41
    POSITIVE LOGITS
     is
    0.60
     be
    0.60
     are
    0.60
     were
    0.59
     ay
    0.57
     was
    0.55
    ต้อง
    0.52
     μην
    0.48
     must
    0.47
     אינו
    0.47
    Act Density 0.002%

    No Known Activations