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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    welcome
    -0.08
    //----------------------------------------------------------------------------↵
    -0.08
     smb
    -0.07
    (Employee
    -0.07
    _ANDROID
    -0.07
    Share
    -0.07
    뺑
    -0.07
     البرلم
    -0.07
     Eg
    -0.07
     lifelong
    -0.07
    POSITIVE LOGITS
    _orig
    0.07
    iga
    0.07
    _MASK
    0.07
    _pcm
    0.07
    characters
    0.07
    _en
    0.06
    alcon
    0.06
     casa
    0.06
     siguiente
    0.06
    _ant
    0.06
    Act Density 0.009%

    No Known Activations