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

    Neuronpedia

    INDEX
    Explanations

    saturation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rede
    -0.07
    -word
    -0.06
     stimulated
    -0.06
    PasswordEncoder
    -0.06
     Assess
    -0.06
    Gün
    -0.06
    킨
    -0.06
     jeans
    -0.06
    BY
    -0.06
    (dict
    -0.06
    POSITIVE LOGITS
    ！");↵
    0.07
    。那
    0.07
     πο
    0.07
     mega
    0.07
    戶
    0.06
     NFC
    0.06
    .");
↵
    0.06
     fc
    0.06
     ){
↵
    0.06
     samozřejmě
    0.06
    Act Density 0.001%

    No Known Activations