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

    Neuronpedia

    INDEX
    Explanations

    own or another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mur
    0.41
     middle
    0.39
     Mous
    0.37
     murah
    0.37
    illian
    0.37
     Mur
    0.36
    icyclic
    0.36
    <unused1092>
    0.36
    inely
    0.36
     encrypted
    0.36
    POSITIVE LOGITS
     ANOTHER
    0.63
     другую
    0.63
    自身的
    0.62
     another
    0.61
     másik
    0.61
     own
    0.60
     নিজেও
    0.60
     eigenen
    0.59
     próprio
    0.59
    另一个
    0.57
    Act Density 0.299%

    No Known Activations