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

    Neuronpedia

    INDEX
    Explanations

    RTL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chang
    -0.07
    lying
    -0.06
    Baş
    -0.06
     Citizen
    -0.06
     служ
    -0.06
    <O
    -0.06
    .lazy
    -0.06
    학년
    -0.06
     killings
    -0.06
     voz
    -0.06
    POSITIVE LOGITS
    oseconds
    0.07
    ٔ
    0.07
    PELL
    0.06
    PT
    0.06
     certainly
    0.06
    beeld
    0.06
    DLL
    0.06
     fullscreen
    0.06
     aberr
    0.06
     propulsion
    0.06
    Act Density 0.003%

    No Known Activations