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

    Neuronpedia

    INDEX
    Explanations

    difference, submission, error, problematic, marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "/"
    0.36
    льную
    0.34
    )".
    0.32
    "+"
    0.30
    )”.
    0.30
    ayant
    0.30
    ⁣⁣
    0.30
    žne
    0.30
    /*!
    0.29
    していて
    0.29
    POSITIVE LOGITS
     ción
    0.37
     tions
    0.34
     tion
    0.33
     sion
    0.29
     aon
    0.29
     оба
    0.29
     ered
    0.28
     ইউন
    0.27
     ence
    0.27
     Both
    0.27
    Act Density 0.010%

    No Known Activations