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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    送
    -0.08
    cer
    -0.07
     led
    -0.07
    ┭
    -0.07
     לנ
    -0.07
     open
    -0.06
     sendMessage
    -0.06
    .send
    -0.06
    aked
    -0.06
     half
    -0.06
    POSITIVE LOGITS
    的母亲
    0.07
    труд
    0.07
     Funeral
    0.07
    荮
    0.07
    _fds
    0.07
    뻡
    0.07
     의미
    0.07
    )'],↵
    0.07
    _lm
    0.07
    atype
    0.07
    Act Density 0.080%

    No Known Activations