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

    Neuronpedia

    INDEX
    Explanations

    sensitivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LS
    -0.06
     Cho
    -0.06
     Dead
    -0.06
     increments
    -0.06
     teleport
    -0.06
    .db
    -0.06
    JP
    -0.06
     vars
    -0.06
     ELEMENT
    -0.06
     Bern
    -0.05
    POSITIVE LOGITS
    acen
    0.07
    "},{"
    0.06
     ",");↵
    0.06
    グル
    0.06
    čer
    0.06
     cmake
    0.06
     dễ
    0.06
    Va
    0.06
     DropDownList
    0.06
    sol
    0.06
    Act Density 0.002%

    No Known Activations