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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lates
    -0.07
    开展
    -0.07
    作者
    -0.07
    .TEXT
    -0.07
    ulator
    -0.06
    .'/'.$
    -0.06
    젤
    -0.06
    $smarty
    -0.06
     роботу
    -0.06
     Scala
    -0.06
    POSITIVE LOGITS
    imming
    0.08
     harmon
    0.07
     blessings
    0.07
    IVING
    0.07
     pil
    0.07
     ))↵↵
    0.07
     Environmental
    0.07
     diligent
    0.06
    '))↵↵
    0.06
    (freq
    0.06
    Act Density 0.000%

    No Known Activations