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

    Neuronpedia

    INDEX
    Explanations

    speaker's past experiences and observations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resulted
    1.06
     resembled
    0.97
    其
    0.95
     attracted
    0.93
     its
    0.90
     necessitated
    0.90
     underwent
    0.89
     transpired
    0.88
     occurred
    0.88
     originated
    0.88
    POSITIVE LOGITS
     heard
    1.13
     known
    1.11
     Known
    1.09
     conocido
    1.07
    Known
    1.06
     never
    1.03
     conhecido
    1.03
     извест
    0.98
     conocida
    0.97
     hears
    0.96
    Act Density 0.228%

    No Known Activations