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

    Neuronpedia

    INDEX
    Explanations

    python code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hawk
    0.57
    ledem
    0.56
     środow
    0.56
    ৈ
    0.55
    ;
    0.55
    דע
    0.54
     occupies
    0.53
     நா
    0.52
    dem
    0.51
    党
    0.51
    POSITIVE LOGITS
     """
    0.87
     》
    0.86
     '''
    0.80
     ."
    0.77
     resveratrol
    0.77
     Burger
    0.77
    .")]
    0.75
    >):
    0.75
     Tidak
    0.75
    örter
    0.75
    Act Density 0.031%

    No Known Activations