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
     Nack
    -0.08
    achelor
    -0.07
     preschool
    -0.07
     proportion
    -0.07
    hlas
    -0.07
     Heather
    -0.07
     tomatoes
    -0.07
    anden
    -0.07
     haste
    -0.07
     principally
    -0.06
    POSITIVE LOGITS
     안전
    0.06
     lake
    0.06
    226
    0.06
    .SDK
    0.06
    _SEC
    0.06
    EHICLE
    0.06
    ев
    0.06
    "];
    0.06
     SECURITY
    0.06
    _PATH
    0.05
    Act Density 0.002%

    No Known Activations