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

    Neuronpedia

    INDEX
    Explanations

    license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .psi
    -0.07
     bliss
    -0.07
    пос
    -0.06
     Beat
    -0.06
     територ
    -0.06
     майбут
    -0.06
    ΟΤ
    -0.06
    们
    -0.06
     виріш
    -0.06
    党
    -0.06
    POSITIVE LOGITS
    schedule
    0.07
    imary
    0.06
     stumbling
    0.06
     picture
    0.06
    kinci
    0.06
    ]}
    0.06
     stroll
    0.06
     sqlite
    0.06
    -down
    0.06
    _mid
    0.06
    Act Density 0.002%

    No Known Activations