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

    Neuronpedia

    INDEX
    Explanations

    cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逆
    -0.07
     Venom
    -0.06
    ασ
    -0.06
     breeds
    -0.06
    िग
    -0.06
    礼
    -0.06
     plaque
    -0.06
     crates
    -0.06
    monic
    -0.06
    .loop
    -0.06
    POSITIVE LOGITS
    "';
    0.07
     UserDao
    0.07
     RF
    0.07
     �
    0.06
     journalist
    0.06
    ]=
    0.06
     ++)
    0.06
    !')↵↵
    0.06
    ص
    0.06
                
↵
    0.06
    Act Density 0.175%

    No Known Activations