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

    Neuronpedia

    INDEX
    Explanations

    what drives needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ris
    0.76
    ótes
    0.73
    োট
    0.71
     এক্ষ
    0.66
    धे
    0.66
    ppies
    0.64
    ajte
    0.64
    ijke
    0.63
    禕
    0.63
    iges
    0.63
    POSITIVE LOGITS
     prompted
    2.52
     prompting
    2.17
     inspired
    2.01
     motivates
    1.98
     motivate
    1.97
     motivating
    1.90
     inspire
    1.87
     spurred
    1.85
     motivated
    1.85
     prompt
    1.83
    Act Density 0.340%

    No Known Activations