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
     Souls
    -0.07
    LogLevel
    -0.07
     hậu
    -0.07
     phi
    -0.06
    .Management
    -0.06
     đoạn
    -0.06
     anime
    -0.06
     روست
    -0.06
    �
    -0.06
    _letters
    -0.06
    POSITIVE LOGITS
    .Read
    0.07
     Addresses
    0.07
     distract
    0.06
    igne
    0.06
    .wh
    0.06
    移动
    0.06
    .rad
    0.06
    osphere
    0.06
    No
    0.06
     Protected
    0.06
    Act Density 0.037%

    No Known Activations