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

    Neuronpedia

    INDEX
    Explanations

    pairs of related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     কাউন্সিল
    0.43
     interf
    0.41
     CORE
    0.40
     बंगला
    0.40
     CONTROL
    0.40
    ্রাজ
    0.40
     SALES
    0.39
    writeObject
    0.39
    ᱲ
    0.39
     FISHER
    0.39
    POSITIVE LOGITS
    irinha
    0.42
    drink
    0.39
     brew
    0.38
     فاذا
    0.38
    つま
    0.38
    透露
    0.38
     لیک
    0.38
     وتش
    0.37
     וח
    0.37
    inee
    0.36
    Act Density 0.000%

    No Known Activations