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

    Neuronpedia

    INDEX
    Explanations

    finding relevant parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whose
    0.49
     even
    0.44
     gotten
    0.43
     ș
    0.43
     probationary
    0.41
     RS
    0.41
     usually
    0.41
    َب
    0.40
     worksheets
    0.40
     kinda
    0.39
    POSITIVE LOGITS
     развитии
    0.47
    tourism
    0.45
     Schönheit
    0.44
     развитие
    0.44
    更多
    0.43
    centres
    0.43
     humanidad
    0.43
    食用
    0.42
     развитию
    0.42
     modernisation
    0.42
    Act Density 0.001%

    No Known Activations