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

    Neuronpedia

    INDEX
    Explanations

    non-English, code, or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Section
    0.40
     ["
    0.38
    ogeneities
    0.36
    {{
    0.36
    Sections
    0.36
     section
    0.36
     dě
    0.36
     collectif
    0.36
    UGS
    0.35
    ണ്ടും
    0.35
    POSITIVE LOGITS
    ดัง
    0.44
    |=|
    0.39
    하이
    0.39
    SMB
    0.38
    aib
    0.38
    অন
    0.37
     фона
    0.37
     Кла
    0.37
     عامل
    0.37
    uniary
    0.37
    Act Density 0.001%

    No Known Activations