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

    Neuronpedia

    INDEX
    Explanations

    Russian language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MI
    -0.08
    ��
    -0.08
     Duncan
    -0.08
     discrimin
    -0.07
    /.↵↵
    -0.07
    /SP
    -0.07
     candidats
    -0.07
    /javase
    -0.07
     CI
    -0.07
     gé
    -0.07
    POSITIVE LOGITS
    ovna
    0.10
    ична
    0.09
    ovich
    0.08
     fabricated
    0.08
    oving
    0.08
    ভাবে
    0.08
    సారి
    0.08
     dynasty
    0.08
    dale
    0.08
    suffix
    0.08
    Act Density 0.007%

    No Known Activations