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

    Neuronpedia

    INDEX
    Explanations

    arrang / arrangement / GPT / bathroom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اريات
    0.68
    abort
    0.68
    ズニー
    0.64
     oluşan
    0.64
    መት
    0.64
    кую
    0.63
    liferation
    0.63
    aguchi
    0.63
    عيب
    0.63
     Desenvolvimento
    0.63
    POSITIVE LOGITS
     arrang
    0.68
     di
    0.66
     control
    0.64
    নীর
    0.61
     by
    0.61
     GL
    0.60
     point
    0.60
     arrangement
    0.59
     origin
    0.59
     pou
    0.58
    Act Density 0.000%

    No Known Activations