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

    Neuronpedia

    INDEX
    Explanations

    lact

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    请点击
    -0.07
    唏
    -0.07
    .vis
    -0.07
     farewell
    -0.07
     inspiration
    -0.07
     WLAN
    -0.07
     steel
    -0.07
     airports
    -0.07
    bursement
    -0.07
    Sidebar
    -0.07
    POSITIVE LOGITS
     pharmac
    0.07
     Cats
    0.07
    ocoa
    0.07
    Cancellation
    0.07
     rằng
    0.07
     mounts
    0.07
     Graduate
    0.06
    嗅
    0.06
     miraculous
    0.06
    的说法
    0.06
    Act Density 0.004%

    No Known Activations