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

    Neuronpedia

    INDEX
    Explanations

    specific nouns and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    1.20
    на
    1.09
    ਾ
    0.98
    certain
    0.89
     অবশ্যই
    0.89
    м
    0.89
     IMPORTANT
    0.88
    א
    0.88
    чам
    0.85
    у
    0.85
    POSITIVE LOGITS
     Parton
    0.89
    镜像
    0.89
     Hogwarts
    0.88
     Dubey
    0.88
    न्देल
    0.88
     biofuels
    0.86
     Ravi
    0.84
    邱
    0.84
    वानगी
    0.84
     Mimi
    0.82
    Act Density 0.000%

    No Known Activations