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

    Neuronpedia

    INDEX
    Explanations

    clarity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yaklaşık
    -0.08
    crypt
    -0.07
    )،
    -0.06
     عص
    -0.06
    professional
    -0.06
    .validation
    -0.06
     photoc
    -0.06
    546
    -0.06
     velit
    -0.06
    .hu
    -0.06
    POSITIVE LOGITS
     opt
    0.07
    deliver
    0.06
    .handler
    0.06
     nedenle
    0.06
     미
    0.06
    Battery
    0.06
    Neutral
    0.06
     Definitely
    0.06
    ecided
    0.06
     státní
    0.06
    Act Density 0.026%

    No Known Activations