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

    Neuronpedia

    INDEX
    Explanations

    file reading and response handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্লো
    0.42
    ﭜ
    0.42
     quals
    0.41
    гать
    0.41
    міст
    0.40
    浻
    0.40
    тоў
    0.40
    Prospect
    0.39
    Ꮺ
    0.38
    𝓗
    0.38
    POSITIVE LOGITS
     Calculate
    0.53
     */
    0.46
     Find
    0.46
     *
    0.45
     Python
    0.45
     Get
    0.45
     calculate
    0.44
    if
    0.43
     Set
    0.43
     Switch
    0.42
    Act Density 0.021%

    No Known Activations