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

    Neuronpedia

    INDEX
    Explanations

    struck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vers
    -0.07
    Hack
    -0.06
    ِّ
    -0.06
     Роз
    -0.06
     rl
    -0.06
     toutes
    -0.06
     leaks
    -0.06
    Representation
    -0.06
    udes
    -0.06
    Comments
    -0.06
    POSITIVE LOGITS
     ایت
    0.07
     PSA
    0.07
    鳥
    0.06
     pace
    0.06
    Friend
    0.06
    _IMAGES
    0.06
    .espresso
    0.06
    [],↵
    0.06
    .aspect
    0.06
     phone
    0.06
    Act Density 0.022%

    No Known Activations