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

    Neuronpedia

    INDEX
    Explanations

    in or after list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Decisions
    0.66
    ō
    0.64
     RO
    0.61
     COVID
    0.61
     February
    0.60
     LGBTQ
    0.59
     $\
    0.58
     đưa
    0.57
     $\$
    0.57
     flagship
    0.56
    POSITIVE LOGITS
    ﺨ
    1.01
    胫
    1.00
    ﯿ
    0.96
     zprac
    0.96
    ﺘ
    0.94
     формы
    0.92
     bristles
    0.90
    ﺪ
    0.88
     школы
    0.88
     beauties
    0.87
    Act Density 0.001%

    No Known Activations