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

    Neuronpedia

    INDEX
    Explanations

    read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hế
    -0.08
    ennent
    -0.07
    簖
    -0.07
    								
↵
    -0.07
     pais
    -0.07
    帧
    -0.07
    ש
    -0.07
    🚗
    -0.07
     Preserve
    -0.07
     fj
    -0.07
    POSITIVE LOGITS
    &&
    0.07
     energy
    0.07
    Generated
    0.07
    虸
    0.06
     minions
    0.06
     group
    0.06
    _ln
    0.06
     PRODUCTS
    0.06
    Legend
    0.06
     обла
    0.06
    Act Density 0.001%

    No Known Activations