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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nếu
    -0.06
    蘇
    -0.06
     kiện
    -0.06
     Î
    -0.06
     chlap
    -0.06
     elevate
    -0.05
    Plot
    -0.05
    ankind
    -0.05
    otte
    -0.05
     steroid
    -0.05
    POSITIVE LOGITS
    ...",↵
    0.07
    _protocol
    0.07
    �
    0.07
    fonts
    0.07
    _PRI
    0.07
    extends
    0.07
     enr
    0.07
    itbart
    0.06
    perimental
    0.06
    _collections
    0.06
    Act Density 0.016%

    No Known Activations