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

    Neuronpedia

    INDEX
    Explanations

    user input and data analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    তরাং
    0.40
    ಳ್ಳಿ
    0.39
    অন্য
    0.38
    山の
    0.38
    रोज
    0.37
    Py
    0.36
    llll
    0.36
    ußen
    0.36
    山的
    0.36
    тыми
    0.35
    POSITIVE LOGITS
     profiles
    0.46
     tuning
    0.41
     jornada
    0.40
     Hab
    0.40
     Tribunal
    0.37
     അവരുടെ
    0.37
     preferences
    0.37
    残酷
    0.37
     durante
    0.37
     centric
    0.36
    Act Density 0.058%

    No Known Activations