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

    Neuronpedia

    INDEX
    Explanations

    conditional checks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Create
    0.67
    \
    0.67
     fürs
    0.66
    E
    0.63
    Brand
    0.63
    Show
    0.61
    رو
    0.59
    qu
    0.58
    Pause
    0.58
    generate
    0.57
    POSITIVE LOGITS
     cisplatin
    0.73
     наличие
    0.68
     className
    0.67
     militant
    0.67
     racist
    0.67
     obliga
    0.64
     एखा
    0.64
     является
    0.64
     celui
    0.63
     receptor
    0.63
    Act Density 0.190%

    No Known Activations