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

    Neuronpedia

    INDEX
    Explanations

    deal-breaker or absolute no

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    知識
    0.77
    Vil
    0.76
     Var
    0.76
    Var
    0.75
     Ny
    0.75
     Helsing
    0.72
    vart
    0.70
    ippi
    0.70
     hjem
    0.69
     Sø
    0.69
    POSITIVE LOGITS
    एडा
    0.67
     বাধা
    0.63
     присутствует
    0.63
     menimbulkan
    0.61
     Geophysical
    0.60
     ges
    0.58
    ദീ
    0.58
     hot
    0.57
     следует
    0.56
     باید
    0.56
    Act Density 0.001%

    No Known Activations