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

    Neuronpedia

    INDEX
    Explanations

    Wellington and Wellington boots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.98
    d
    0.98
    är
    0.87
    k
    0.85
    ur
    0.84
    ся
    0.83
    ל
    0.82
    x
    0.79
    న్
    0.79
    ng
    0.77
    POSITIVE LOGITS
    ম
    0.89
    ับ
    0.79
    >$
    0.79
    arono
    0.79
    م
    0.79
    مع
    0.78
     Wellington
    0.78
    >
    0.75
    يب
    0.75
    ר
    0.74
    Act Density 0.001%

    No Known Activations