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

    Neuronpedia

    INDEX
    Explanations

    OWASP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Won
    0.40
     Oo
    0.39
     লজ্জ
    0.38
    แต่ง
    0.38
    寳
    0.36
     giành
    0.35
    নো
    0.35
    won
    0.34
     એમ
    0.34
    尺度
    0.34
    POSITIVE LOGITS
     negativa
    0.42
    собенно
    0.40
     Brad
    0.38
     surtout
    0.37
    ium
    0.36
     तथा
    0.36
    vap
    0.35
     machining
    0.35
     stratification
    0.35
     illetve
    0.35
    Act Density 0.001%

    No Known Activations