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

    Neuronpedia

    INDEX
    Explanations

    ex-boyfriend, ex-partner, exosome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IS
    0.98
    n
    0.98
    "
    0.93
    _
    0.93
    NE
    0.92
    June
    0.92
     snugly
    0.89
    お
    0.88
    ন
    0.88
    ান
    0.87
    POSITIVE LOGITS
     (
    1.08
    ções
    0.93
    s
    0.88
     ex
    0.86
    ningar
    0.83
    ige
    0.81
    ներ
    0.81
    ים
    0.80
    ного
    0.79
    ją
    0.79
    Act Density 0.007%

    No Known Activations