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

    Neuronpedia

    INDEX
    Explanations

    HTML anchor href attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TESTS
    0.37
     किफ
    0.37
     मैत्री
    0.36
    ीण
    0.36
    ╞
    0.36
    ႉ
    0.35
    อิ
    0.35
     merveille
    0.34
     ModInt
    0.34
     kiire
    0.33
    POSITIVE LOGITS
     #
    0.82
     '#'
    0.82
    ="#">
    0.79
     "#
    0.77
     (#
    0.76
    javascript
    0.75
     '#
    0.74
     \#
    0.74
    ="#"
    0.71
    ＃
    0.71
    Act Density 0.002%

    No Known Activations