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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and arrows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ０
    1.16
    𝟘
    0.96
     at
    0.95
     tentang
    0.94
     සහ
    0.94
    вла
    0.91
    𝟬
    0.89
     ০
    0.88
    of
    0.87
     عن
    0.85
    POSITIVE LOGITS
    ↵
    1.52
    '
    0.95
    在
    0.87
    n
    0.86
    ও
    0.84
    a
    0.77
     miss
    0.73
     CH
    0.71
     JAVA
    0.71
    きます
    0.70
    Act Density 0.012%

    No Known Activations