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

    Neuronpedia

    INDEX
    Explanations

    code statements or function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     موارد
    0.38
    0.37
     이러한
    0.37
     typology
    0.37
    ម្រ
    0.37
     semblable
    0.37
     नसल्या
    0.36
    }^{+}(
    0.36
     সেইরূপ
    0.36
     खड़े
    0.34
    POSITIVE LOGITS
     inside
    0.62
     estoy
    0.55
    我是
    0.54
    吃饭
    0.54
     Inside
    0.54
     AGAIN
    0.52
     here
    0.52
    我可以
    0.50
     jsem
    0.50
     jestem
    0.50
    Act Density 0.016%

    No Known Activations