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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Proveedor
    -0.08
    EEE
    -0.07
     रह
    -0.07
    ugen
    -0.07
    Lee
    -0.07
    응
    -0.07
    pray
    -0.07
    =Y
    -0.06
     Wu
    -0.06
    imu
    -0.06
    POSITIVE LOGITS
    (cos
    0.07
     combine
    0.07
     ""),↵
    0.07
    :#
    0.06
    +↵
    0.06
    ?,
    0.06
     urlString
    0.06
     ")"↵
    0.06
     "','
    0.06
     early
    0.06
    Act Density 0.019%

    No Known Activations