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

    Neuronpedia

    INDEX
    Explanations

    arguments for actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     allowable
    0.52
     predomin
    0.50
    E
    0.48
    за
    0.46
    тер
    0.46
    are
    0.45
    Ма
    0.45
     are
    0.44
    Пор
    0.43
    Д
    0.43
    POSITIVE LOGITS
     touristic
    0.91
     nowadays
    0.80
     enthous
    0.80
     Nowadays
    0.80
     advices
    0.77
     loosing
    0.71
     (=
    0.69
    splitted
    0.67
     ressources
    0.67
     bellow
    0.64
    Act Density 0.056%

    No Known Activations