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

    Neuronpedia

    INDEX
    Explanations

    say "the ending -ings"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Copp
    -0.09
    再也没有
    -0.07
    (rhs
    -0.07
     Newport
    -0.07
     original
    -0.07
     gateway
    -0.07
    仍然是
    -0.07
     obscure
    -0.07
    .stock
    -0.07
    都不知道
    -0.07
    POSITIVE LOGITS
     CW
    0.08
    Cumhur
    0.06
    Radians
    0.06
    躬
    0.06
    Ⱐ
    0.06
     CRUD
    0.06
     Resist
    0.06
    uzzy
    0.06
    ญ
    0.06
    牵挂
    0.06
    Act Density 0.001%

    No Known Activations