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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thu
    -0.07
     moment
    -0.07
    �
    -0.07
     precip
    -0.07
    _FEATURE
    -0.07
    所在
    -0.06
     Cd
    -0.06
    erra
    -0.06
    ↵↵↵↵↵↵↵↵
    -0.06
    Andy
    -0.06
    POSITIVE LOGITS
    精英
    0.07
    ynec
    0.07
    IEnumerator
    0.07
    awner
    0.07
    icter
    0.07
    肥胖
    0.07
    עלייה
    0.07
    ByName
    0.07
    .prob
    0.07
    sey
    0.06
    Act Density 0.087%

    No Known Activations