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

    Neuronpedia

    INDEX
    Explanations

    cabin / cabins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    the
    0.86
    of
    0.82
    г
    0.77
    라
    0.76
    라고
    0.72
    д
    0.71
    (),
    0.71
    する
    0.71
    ות
    0.69
     curator
    0.69
    POSITIVE LOGITS
     cabins
    1.04
     cottages
    0.88
    Cabin
    0.88
    mén
    0.86
     cabin
    0.85
    rante
    0.81
    rů
    0.80
    пону
    0.79
    rätt
    0.79
     Cabin
    0.76
    Act Density 0.006%

    No Known Activations