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

    Neuronpedia

    INDEX
    Explanations

    word completion and phrase continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    мі
    0.47
     Hindu
    0.47
    ادیه
    0.47
     Patience
    0.46
     greed
    0.46
     majesty
    0.44
     Maharaja
    0.44
     hindu
    0.44
     patience
    0.44
     scriptures
    0.44
    POSITIVE LOGITS
     школова
    0.49
    faced
    0.45
     buildFor
    0.44
     negotiable
    0.43
     предлага
    0.42
    Vac
    0.42
    Со
    0.42
    negoti
    0.41
    Work
    0.41
    nearly
    0.41
    Act Density 0.000%

    No Known Activations