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

    Neuronpedia

    INDEX
    Explanations

    words preceding common sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     приго
    0.47
     вроде
    0.46
     கொஞ்சம்
    0.45
     Luckily
    0.43
     Leave
    0.43
     Honestly
    0.43
     могло
    0.42
     зато
    0.42
    ちょっと
    0.42
    Honestly
    0.41
    POSITIVE LOGITS
     eigen
    0.54
     library
    0.49
     bytecode
    0.49
     filmm
    0.46
     tomography
    0.46
     therapeutics
    0.46
     technique
    0.45
     comics
    0.45
     executable
    0.45
     reactivity
    0.45
    Act Density 0.001%

    No Known Activations