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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ax
    -0.07
    Logging
    -0.07
    ymous
    -0.07
     Turing
    -0.07
    conda
    -0.07
    Called
    -0.07
     TIMER
    -0.06
     kỳ
    -0.06
    .CONNECT
    -0.06
    Tên
    -0.06
    POSITIVE LOGITS
    -&
    0.09
     astronomers
    0.07
     service
    0.07
    �
    0.07
    科研院
    0.07
    _admin
    0.07
    (worker
    0.07
    剜
    0.07
    .localization
    0.06
    _sep
    0.06
    Act Density 0.001%

    No Known Activations