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

    Neuronpedia

    INDEX
    Explanations

    to be or have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     а
    0.85
     a
    0.68
    AL
    0.68
    あ
    0.67
     the
    0.64
    이랑
    0.64
     மற்றும்
    0.63
    बल
    0.62
    о
    0.62
     알
    0.62
    POSITIVE LOGITS
     aberrations
    0.66
    ¹
    0.64
     etched
    0.63
     tincture
    0.63
     realizzato
    0.61
     ermöglichen
    0.60
     indel
    0.59
    sächlich
    0.59
    ,’
    0.59
     विस्तार
    0.59
    Act Density 0.861%

    No Known Activations