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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming constructs and user interface elements

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

    add_control / control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tikang
    -0.53
    AppMethodBeat
    -0.46
    舺
    -0.45
     lenker
    -0.45
     jäsen
    -0.45
     París
    -0.44
     bière
    -0.44
     المعيارى
    -0.42
     ammat
    -0.42
     дописавши
    -0.42
    POSITIVE LOGITS
     control
    1.22
    control
    1.07
     controls
    1.00
    ontrol
    0.98
    controls
    0.94
     kontrol
    0.92
     Control
    0.90
    CONTROL
    0.89
    Control
    0.88
     CONTROL
    0.87
    Act Density 0.016%

    No Known Activations