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

    Neuronpedia

    INDEX
    Explanations

    specimen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    河
    -0.07
     cres
    -0.07
     Ch
    -0.07
    戴
    -0.07
     Burg
    -0.07
     که
    -0.07
    juana
    -0.06
     Index
    -0.06
    랑스
    -0.06
     schöne
    -0.06
    POSITIVE LOGITS
    純
    0.06
     kullanıcı
    0.06
     одного
    0.06
     FUCK
    0.05
     úspě
    0.05
     şart
    0.05
     बदल
    0.05
    /img
    0.05
     kind
    0.05
     případě
    0.05
    Act Density 0.019%

    No Known Activations