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
    ponsible
    -0.06
     interacts
    -0.06
    OSE
    -0.06
     story
    -0.06
     PKK
    -0.06
     Vienna
    -0.06
    대
    -0.06
    rail
    -0.06
     jiných
    -0.06
    rolled
    -0.06
    POSITIVE LOGITS
    �
    0.07
    /yyyy
    0.07
     Symptoms
    0.06
    /mL
    0.06
    Violation
    0.06
     json
    0.06
     Latinos
    0.06
    %,
    0.06
    ней
    0.06
    Reg
    0.06
    Act Density 0.005%

    No Known Activations