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

    Neuronpedia

    INDEX
    Explanations

    templating syntax expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಓ
    0.46
    溽
    0.43
     ಅಪ
    0.43
    岡山
    0.42
    ミン
    0.42
     провин
    0.41
    physema
    0.41
    necked
    0.41
    APAN
    0.40
    Schmidt
    0.40
    POSITIVE LOGITS
     {{
    1.04
    {{
    0.96
    ({{
    0.81
    }}{{
    0.80
     "{{
    0.79
     {{-
    0.77
    {%
    0.76
    ="{{
    0.75
     %}
    0.73
    ">{{
    0.72
    Act Density 0.020%

    No Known Activations