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

    Neuronpedia

    INDEX
    Explanations

    Scheduling meetings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ибли
    -0.07
     Liga
    -0.07
    実
    -0.07
    amin
    -0.07
     forgive
    -0.06
    ayer
    -0.06
     Ninh
    -0.06
     Silence
    -0.06
     via
    -0.06
     Alexandre
    -0.06
    POSITIVE LOGITS
    unded
    0.06
    )!↵
    0.06
    (head
    0.06
     escre
    0.06
    Carol
    0.06
    証
    0.06
    ुद
    0.06
    лод
    0.06
     ألمان
    0.06
    ))}↵
    0.06
    Act Density 0.058%

    No Known Activations