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

    Neuronpedia

    INDEX
    Explanations

    my ethical purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stuff
    0.67
     WR
    0.64
    wr
    0.64
     flavors
    0.63
     পালা
    0.62
     мело
    0.62
    Smoking
    0.61
     letra
    0.61
    葡萄酒
    0.58
    ad
    0.57
    POSITIVE LOGITS
    倫
    0.86
     fondateur
    0.78
     શકે
    0.78
     malfunction
    0.76
    伦
    0.76
     functioned
    0.75
     expanded
    0.75
     deactivate
    0.75
    BPACK
    0.75
     technician
    0.74
    Act Density 0.500%

    No Known Activations