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

    Neuronpedia

    INDEX
    Explanations

    special days and observances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Halloween
    0.68
     Thanksgiving
    0.68
     aniversario
    0.66
     festival
    0.65
     Día
    0.65
     Ramadan
    0.64
     commemor
    0.64
     celebración
    0.64
     anniversary
    0.61
     annivers
    0.61
    POSITIVE LOGITS
    aptan
    0.39
    Airplane
    0.38
    如果
    0.38
    Lightning
    0.38
    Get
    0.37
    เท
    0.37
     leftovers
    0.37
    自分で
    0.36
     leftover
    0.36
    〃
    0.36
    Act Density 0.002%

    No Known Activations