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

    Neuronpedia

    INDEX
    Explanations

    preparing tables or pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verwand
    0.47
     is
    0.46
     anderes
    0.45
     bese
    0.45
    晚上
    0.44
     kleine
    0.44
    食物
    0.43
     indépend
    0.43
     independientes
    0.43
    砚
    0.43
    POSITIVE LOGITS
     ҳу
    0.49
    ुलकर
    0.47
    ulas
    0.46
     उन्नत
    0.46
     Serbian
    0.46
    ermanfaat
    0.45
     Clayton
    0.45
    propertyPath
    0.45
     Mugabe
    0.43
     یا
    0.43
    Act Density 0.001%

    No Known Activations