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

    Neuronpedia

    INDEX
    Explanations

    compound noun completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.53
    ப்படுகின்றன
    0.46
     naudoj
    0.46
     the
    0.45
    čních
    0.45
     North
    0.44
    它们
    0.43
     dalam
    0.43
    altungen
    0.43
     National
    0.42
    POSITIVE LOGITS
    тник
    0.46
    קה
    0.45
    ｸ
    0.44
    КА
    0.44
    кс
    0.43
     ছবিটি
    0.43
     ሰው
    0.43
    }$&$-
    0.43
    ртка
    0.43
    ObjectTemp
    0.41
    Act Density 0.183%

    No Known Activations