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

    Neuronpedia

    INDEX
    Explanations

    terms related to user interface elements and functional programming constructs in code

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

    data target id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CanadaChoose
    -0.47
    licherweise
    -0.40
    Disposable
    -0.37
     netto
    -0.36
     gé
    -0.35
     fileSize
    -0.35
    Bissau
    -0.35
    mühle
    -0.34
    FileOutputStream
    -0.34
    FloatField
    -0.34
    POSITIVE LOGITS
    target
    1.07
     target
    0.87
    Target
    0.84
     Target
    0.82
    TARGET
    0.75
    StoryboardSegue
    0.70
     TARGET
    0.69
     Targets
    0.67
    arget
    0.65
    Targets
    0.65
    Act Density 0.004%

    No Known Activations