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
    .findall
    -0.07
    场
    -0.07
    _LED
    -0.07
    �
    -0.07
    ,'%
    -0.06
    _cert
    -0.06
    жи
    -0.06
    =time
    -0.06
     (`
    -0.06
     Fare
    -0.06
    POSITIVE LOGITS
    orestation
    0.07
    ventus
    0.07
    .edu
    0.07
     dealing
    0.06
     tackle
    0.06
    192
    0.06
     comfortably
    0.06
     basics
    0.06
     traits
    0.06
     assists
    0.06
    Act Density 0.001%

    No Known Activations