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

    Neuronpedia

    INDEX
    Explanations

    names after @

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hippocamp
    0.67
     epistle
    0.65
    ัน
    0.64
    ానికి
    0.64
     duvet
    0.62
     elegante
    0.60
    р
    0.60
    ո
    0.60
    ри
    0.60
     bás
    0.59
    POSITIVE LOGITS
    to
    1.02
    na
    0.90
    x
    0.88
    f
    0.81
     to
    0.80
    this
    0.77
    re
    0.76
    no
    0.75
    my
    0.73
    0
    0.72
    Act Density 0.040%

    No Known Activations