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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dialogs
    -0.08
    imu
    -0.07
     rapper
    -0.07
    ベ
    -0.07
    ître
    -0.07
    uries
    -0.07
     обще
    -0.07
    oslav
    -0.07
    олева
    -0.07
     博
    -0.07
    POSITIVE LOGITS
     ש
    0.05
     circuits
    0.05
    $title
    0.05
    .Metadata
    0.05
     "}\
    0.05
    >--}}↵
    0.05
     résult
    0.05
    .office
    0.05
     escape
    0.05
     skip
    0.05
    Act Density 0.065%

    No Known Activations