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

    Neuronpedia

    INDEX
    Explanations

    describing types of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்த
    0.52
     OWL
    0.47
     motherboard
    0.45
     фай
    0.44
    াৎ
    0.44
    ुट
    0.44
    ナ
    0.44
    вач
    0.43
    OWL
    0.42
    க்ஸாண்ட
    0.42
    POSITIVE LOGITS
     duro
    0.46
    Sustainability
    0.45
    history
    0.44
    overline
    0.43
    cknow
    0.43
    Question
    0.42
     역사
    0.42
    Planning
    0.41
    memset
    0.41
    谍
    0.41
    Act Density 0.000%

    No Known Activations