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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////////////////////////////////////////////////////////////////
    -0.07
     Johnston
    -0.06
    Gender
    -0.06
    ptron
    -0.06
    ᴅ
    -0.06
    ewire
    -0.06
    娱
    -0.06
    -separated
    -0.06
    artic
    -0.06
    ApiKey
    -0.06
    POSITIVE LOGITS
     защиты
    0.08
    移动端
    0.07
     Copenhagen
    0.07
     ace
    0.07
     CS
    0.07
    正在
    0.06
     en
    0.06
    Snackbar
    0.06
    _dummy
    0.06
    拍摄
    0.06
    Act Density 0.063%

    No Known Activations