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

    Neuronpedia

    INDEX
    Explanations

    sentence endings and punctuation marks

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

    Follows a period in technical or formal writing

    np_acts-logits-general · gemini-2.0-flash

    objective or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.73
    `,
    -0.72
     FetchType
    -0.71
    ChildScrollView
    -0.71
     MotionEvent
    -0.69
    󠁮
    -0.66
    Hozzáférés
    -0.65
    `;
    -0.64
    ällor
    -0.64
    enumii
    -0.64
    POSITIVE LOGITS
    Objective
    0.93
     PURPOSE
    0.93
    Abstract
    0.92
     Objective
    0.91
    Purpose
    0.90
     OBJECTIVE
    0.88
     Abstract
    0.83
    ABSTRACT
    0.83
    OBJECTIVE
    0.83
     objective
    0.81
    Act Density 0.909%

    No Known Activations