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

    Neuronpedia

    INDEX
    Explanations

    interpreting evidence and meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.41
    О
    1.23
    ре
    1.22
    ه
    1.09
    est
    1.02
     venezol
    1.02
    ется
    0.97
    ло
    0.97
     tratados
    0.97
    است
    0.96
    POSITIVE LOGITS
     Interpretation
    1.03
     interprets
    0.92
     Interpret
    0.91
    ד
    0.91
    দের
    0.89
     interpret
    0.89
    。“
    0.84
     interpreting
    0.83
    שת
    0.81
    нули
    0.81
    Act Density 0.013%

    No Known Activations