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

    Neuronpedia

    INDEX
    Explanations

    end-of-turn markers or pauses in text sequences

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

    global scope in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.69
    webElementGuid
    -0.68
     ModelExpression
    -0.64
    Parcelize
    -0.63
    +#+#
    -0.62
    lapsingToolbar
    -0.62
    UniformLocation
    -0.60
    GenerationType
    -0.60
    IBOutlet
    -0.60
     المعيارى
    -0.59
    POSITIVE LOGITS
     weltweit
    0.36
     worldwide
    0.35
     wereld
    0.32
    worldwide
    0.32
    全球
    0.31
    并
    0.29
     global
    0.29
    tionalität
    0.29
     legais
    0.29
     drept
    0.29
    Act Density 0.000%

    No Known Activations