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

    Neuronpedia

    INDEX
    Explanations

    exception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Polit
    -0.07
    original
    -0.06
     boilers
    -0.06
    Means
    -0.06
     Guitar
    -0.06
    window
    -0.06
     Hak
    -0.06
     Toni
    -0.06
     rifles
    -0.06
    Branch
    -0.06
    POSITIVE LOGITS
     EXCEPTION
    0.08
     αν
    0.07
     �
    0.07
    ouser
    0.06
    765
    0.06
     �
    0.06
    只要
    0.06
    ランス
    0.06
    ......
    0.06
     DBHelper
    0.06
    Act Density 0.000%

    No Known Activations