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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and their related conjugations

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

    German language and code snippets

    np_acts-logits-general · gemini-2.0-flash

    German and English technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.64
    __*/
    -0.61
    __((
    -0.59
    ⇑
    -0.59
    日閲覧
    -0.55
    DeleteBehavior
    -0.54
    tanleria
    -0.54
    enderror
    -0.53
    ollectionView
    -0.53
     nakalista
    -0.53
    POSITIVE LOGITS
    Viited
    0.54
     Frequencies
    0.51
     SwitchCompat
    0.49
    agissait
    0.48
    styleType
    0.48
    ุ่ม
    0.48
    Життєпис
    0.48
     Procedural
    0.47
    imbawa
    0.47
     Requiem
    0.47
    Act Density 0.054%

    No Known Activations