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

    Neuronpedia

    INDEX
    Explanations

    handle complex, many men, Imagine AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     легко
    0.41
     bury
    0.39
    간다
    0.37
     handling
    0.37
     minima
    0.37
    ধ্যার
    0.36
    帚
    0.36
     જાય
    0.35
    揶
    0.35
     जायें
    0.35
    POSITIVE LOGITS
    Vul
    0.40
     FLAT
    0.39
    ini
    0.39
    imine
    0.38
     AMOLED
    0.38
    igkeit
    0.38
    android
    0.38
    Flat
    0.38
     Андроид
    0.37
    inel
    0.37
    Act Density 0.000%

    No Known Activations