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

    Neuronpedia

    INDEX
    Explanations

    direct, beyond, views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     зміню
    0.45
     vaiht
    0.45
     combustível
    0.44
     змен
    0.44
     chambre
    0.43
    মণ্ড
    0.42
    ونو
    0.42
     бизнеса
    0.41
     умень
    0.40
    ischem
    0.40
    POSITIVE LOGITS
     May
    0.49
    0.47
    은
    0.46
     Norway
    0.45
     ευ
    0.45
    %
    0.44
     Nor
    0.44
     Integration
    0.43
    metic
    0.43
     Beta
    0.43
    Act Density 0.004%

    No Known Activations