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

    Neuronpedia

    INDEX
    Explanations

    words or phrases describing a situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тика
    0.47
    owało
    0.44
    autogui
    0.42
    ot
    0.40
    ќ
    0.40
     Assignments
    0.40
    abytes
    0.39
    エース
    0.39
    襯
    0.39
    om
    0.38
    POSITIVE LOGITS
     esk
    0.40
     molécule
    0.40
     despre
    0.39
     penta
    0.39
     sammen
    0.38
     molé
    0.38
    Pointing
    0.37
     crystallization
    0.37
     produzione
    0.37
     hoje
    0.37
    Act Density 0.000%

    No Known Activations